SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.09697 · 2020

Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 1 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/2010.09697.json · badge: /api/ran/2010.09697.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
viking-sudo-rm/norm-growth canonical (classifier label)
classifier basis: classifier_2025
6 ran · 1 no recorded run
FunctionStatusWhere it lives
cos Ran
ran; our contract draft was wrong, not the code
viking-sudo-rm/norm-growth/eval_pretrain_sat_brown.py
pointer only (licence: NONE) · get_code("6198d16a5879a397")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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.

filter_by_layer Ran
ran; our contract draft was wrong, not the code
viking-sudo-rm/norm-growth/t5_main.py
pointer only (licence: NONE) · get_code("423851dbdaeb3755")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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.

get_checkpoints Ran
ran; our contract draft was wrong, not the code
viking-sudo-rm/norm-growth/t5_main.py
pointer only (licence: NONE) · get_code("73b48f5f7899940d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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.

get_norm Ran
ran, honoured the contract we drafted
viking-sudo-rm/norm-growth/finetune_trans.py
pointer only (licence: NONE) · get_code("f255b17a12b2af42")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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.

get_param_names Ran
ran; our contract draft was wrong, not the code
viking-sudo-rm/norm-growth/t5_main.py
pointer only (licence: NONE) · get_code("f3263e56c9d5df87")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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.

get_sentences Ran
ran; our contract draft was wrong, not the code
viking-sudo-rm/norm-growth/eval_pretrain_sat_brown.py
pointer only (licence: NONE) · get_code("ffc6543d0b4f8d4b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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.

get_projection Not yet run
unverified (harvested, no recorded run)
viking-sudo-rm/norm-growth/finetune_trans.py
pointer only (licence: NONE) · get_code("7d135ddd16507bbb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, viking-sudo-rm/norm-growth 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To better understand this bias, we study the tendency for transformer parameters to grow in magnitude ($\ell_2$ norm) during training, and its implications for the emergent representations within self attention layers. Empirically, we document norm growth in the training of transformer language models, including T5 during its pretraining. As the parameters grow in magnitude, we prove that the network approximates a discretized network with saturated activation functions. Such "saturated" networks are known to have a reduced capacity compared to the full network family that can be described in terms of formal languages and automata. Our results suggest saturation is a new characterization of an inductive bias implicit in GD of particular interest for NLP. We leverage the emergent discrete structure in a saturated transformer to analyze the role of different attention heads, finding that some focus locally on a small number of positions, while other heads compute global averages, allowing counting. We believe understanding the interplay between these two capabilities may shed further light on the structure of computation within large transformers.

For agents

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

get_harvested_code_for_paper("2010.09697")
get_code_for_paper("2010.09697")
have("2010.09697")

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

curl https://syntology.ai/api/ran/2010.09697.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.09697.svg)](https://syntology.ai/paper/2010.09697)

Connect an agent — have() is free.