SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.07229 · 2022

Mass-Editing Memory in a Transformer

Alex Andonian, Yonatan Belinkov, David Bau, Kevin Meng, Arnab Sharma

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2210.07229.json · badge: /api/ran/2210.07229.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
kmeng01/memit canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
binary_log_probs Ran
ran; our contract draft was wrong, not the code
kmeng01/memit/baselines/mend/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from MemEIC/MemEIC, is pointer only (licence: NONE) · get_code("27659a9c234ffb11")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from MemEIC/MemEIC, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hierarchical_subsequence Ran
ran on a synthesized input
kmeng01/memit/util/nethook.py
code served (permissive licence) · get_code("920b394e7ad80c53")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from collections import OrderedDict

torch.manual_seed(0)

# Create a nested Sequential model to test hierarchical_subsequence
layer1 = nn.Linear(4, 3)
layer2 = nn.Linear(3, 2)
layer3 = nn.Linear(2, 5)

nested_seq = nn.Sequential(
    OrderedDict([
        ('linear1', layer1),
        ('linear2', layer2),
        ('linear3', layer3)
    ])
)

# Test case 1: No parameters (should return full sequential)
ARGS = {
    'sequential': nested_seq,
    'first': None,
    'last': None,
    'after': None,
    'upto': None,
    'share_weights': False,
    'depth': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
kl_loc_loss Ran
ran; our contract draft was wrong, not the code
kmeng01/memit/baselines/mend/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("8b02eb3a3733d653")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Wangzzzzzzzz/OTE-SE-Alignment, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

multiclass_log_probs Ran
ran; our contract draft was wrong, not the code
kmeng01/memit/baselines/mend/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("8ccc8886c554a1ce")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Wangzzzzzzzz/OTE-SE-Alignment, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

recursive_copy Ran
ran; our contract draft was wrong, not the code
kmeng01/memit/util/nethook.py
pointer only (licence: MIT); the stored copy get_code serves, from TrustedLLM/UnKE, is pointer only (licence: NONE) · get_code("70f6ab8bde55420e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from TrustedLLM/UnKE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

subsequence Ran
ran; our contract draft was wrong, not the code
kmeng01/memit/util/nethook.py
code served (permissive licence) · get_code("440ff98c2b1ae1aa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import copy
from collections import OrderedDict

torch.manual_seed(0)

# Build a nested Sequential model with multiple layers
sequential = nn.Sequential(
    OrderedDict([
        ('layer1', nn.Linear(4, 3)),
        ('layer2', nn.ReLU()),
        ('layer3', nn.Linear(3, 2)),
        ('nested', nn.Sequential(
            OrderedDict([
                ('sublayer1', nn.Linear(2, 2)),
                ('sublayer2', nn.ReLU()),
            ])
        )),
        ('layer4', nn.Linear(2, 1)),
    ])
)

ARGS = {
    'sequential': sequential,
    'first_layer': None,
    'last_layer': None,
    'after_layer': None,
    'upto_layer': None,
    'single_layer': None,
    'share_weights': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_model Not yet run
unverified (harvested, no recorded run)
kmeng01/memit/baselines/mend/models.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("d9a5bcaef451668f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Wangzzzzzzzz/OTE-SE-Alignment, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
kmeng01/memit/baselines/mend/models.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("87e77d8c9c3620e1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Wangzzzzzzzz/OTE-SE-Alignment, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 8 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
subsequence 49 other papers
3 dated earlier, 46 later
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2009.05041 (2020-09)
Understanding the Role of Individual Units in a Deep Neural Network
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
and 46 more not named here
recursive_copy 48 other papers
1 dated earlier, 47 later
2207.02774 (2022-07)
Local Relighting of Real Scenes
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
and 45 more not named here
hierarchical_subsequence 46 other papers
46 later
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2312.07876 (2023-12)
Causality Analysis for Evaluating the Security of Large Language Models
and 43 more not named here
binary_log_probs 28 other papers
28 later
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
and 25 more not named here
multiclass_log_probs 10 other papers
10 later
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
2401.07453 (2024-01)
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
and 7 more not named here
kl_loc_loss 9 other papers
9 later
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2401.07453 (2024-01)
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
2403.07175 (2024-03)
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
and 6 more not named here
get_model 8 other papers
8 later
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
2401.07453 (2024-01)
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
and 5 more not named here
get_tokenizer 8 other papers
8 later
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
2401.07453 (2024-01)
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
and 5 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent work has shown exciting promise in updating large language models with new memories, so as to replace obsolete information or add specialized knowledge. However, this line of work is predominantly limited to updating single associations. We develop MEMIT, a method for directly updating a language model with many memories, demonstrating experimentally that it can scale up to thousands of associations for GPT-J (6B) and GPT-NeoX (20B), exceeding prior work by orders of magnitude. Our code and data are at memit.baulab.info. How many memories can we add to a deep network by directly editing its weights? Although large autoregressive language models (Radford et al., 2019;Brown et al., 2020;Wang & Komatsuzaki, 2021;Black et al., 2022) are capable of recalling an impressive array of common facts such as "Tim Cook is the CEO of Apple" or "Polaris is in the constellation Ursa Minor" (Petroni et al., 2020;Brown et al., 2020), even very large models are known to lack more specialized knowledge, and they may recall obsolete information if not updated periodically (Lazaridou et al., 2021;Agarwal & Nenkova, 2022;Liska et al., 2022). The ability to maintain fresh and customizable information is desirable in many application domains, such as question answering, knowledge search, and content generation. For example, we might want to keep search models updated with breaking news and recently-generated user feedback. In other situations, authors or companies may wish to customize models with specific knowledge about their creative work or products. Because re-training a large model can be prohibitive (Patterson et al., 2021) we seek methods that can update knowledge directly.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.07229")
get_code_for_paper("2210.07229")
have("2210.07229")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.07229.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.07229.svg)](https://syntology.ai/paper/2210.07229)

Connect an agent — have() is free.