SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.10102 · 2020

Attention is Not Only a Weight: Analyzing Transformers with Vector Norms

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 2 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/2004.10102.json · badge: /api/ran/2004.10102.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
gorokoba560/norm-analysis-of-transformer canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_head_avg Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from gorokoba560/norm-analysis-of-transformer
pointer only; the stored copy get_code serves, from gorokoba560/norm-analysis-of-transformer, is pointer only (licence: NONE) · get_code("6a5f53701e5acc8a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

convert_layer_avg Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from gorokoba560/norm-analysis-of-transformer
pointer only; the stored copy get_code serves, from gorokoba560/norm-analysis-of-transformer, is pointer only (licence: NONE) · get_code("d6d84bf4e3c570a0")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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_word_word_attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gorokoba560/norm-analysis-of-transformer/emnlp2020/exp2_nmt/calculate_aer.py
pointer only (licence: NONE) · get_code("0477f8085bf514b9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorokoba560/norm-analysis-of-transformer 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.

convert_bpe_word Not yet run
unverified (harvested, no recorded run)
gorokoba560/norm-analysis-of-transformer/emnlp2020/exp2_nmt/calculate_aer.py
pointer only (licence: NONE) · get_code("5b78bca2eee14ae0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gorokoba560/norm-analysis-of-transformer 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
convert_head_avg 2 other papers
2 later
2109.07152 (2021-09)
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
2302.00456 (2023-02)
Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
convert_layer_avg 2 other papers
2 later
2109.07152 (2021-09)
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
2302.00456 (2023-02)
Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
get_word_word_attention 1 other paper
1 later
2205.11631 (2022-05)
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer

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

Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing. Hence, attention is being extensively studied to investigate various linguistic capabilities of Transformers, focusing on analyzing the parallels between attention weights and specific linguistic phenomena. This paper shows that attention weights alone are only one of the two factors that determine the output of attention and proposes a norm-based analysis that incorporates the second factor, the norm of the transformed input vectors. The findings of our norm-based analyses of BERT and a Transformer-based neural machine translation system include the following: (i) contrary to previous studies, BERT pays poor attention to special tokens, and (ii) reasonable word alignment can be extracted from attention mechanisms of Transformer. These findings provide insights into the inner workings of Transformers.

For agents

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

get_harvested_code_for_paper("2004.10102")
get_code_for_paper("2004.10102")
have("2004.10102")

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

curl https://syntology.ai/api/ran/2004.10102.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.10102.svg)](https://syntology.ai/paper/2004.10102)

Connect an agent — have() is free.