SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.05041 · 2020

Understanding the Role of Individual Units in a Deep Neural Network

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 3 failures of our instrument; 0 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/2009.05041.json · badge: /api/ran/2009.05041.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
davidbau/dissect canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_ablation_replacement Ran
ran, honoured the contract we drafted
davidbau/dissect/netdissect/nethook.py
pointer only (licence: NOASSERTION) · get_code("e6e2771a0de59277")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, davidbau/dissect (NOASSERTION). 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.

instrumented_layername Ran
ran; our contract draft was wrong, not the code
davidbau/dissect/experiment/dissect_experiment.py
pointer only (licence: NOASSERTION) · get_code("298373443b85a0c0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, davidbau/dissect (NOASSERTION). 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.

make_matching_tensor Ran
ran; our contract draft was wrong, not the code
davidbau/dissect/netdissect/nethook.py
pointer only (licence: NOASSERTION) · get_code("0a92af765d5132e3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, davidbau/dissect (NOASSERTION). 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
davidbau/dissect/netdissect/nethook.py
pointer only (licence: NOASSERTION) · get_code("aa2af4041a7e30bc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, davidbau/dissect (NOASSERTION). 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.

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 (3 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
subsequence 49 other papers
1 dated earlier, 48 later
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
and 46 more not named here
apply_ablation_replacement 4 other papers
2 dated earlier, 2 later
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
and 1 more not named here
make_matching_tensor 4 other papers
2 dated earlier, 2 later
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
and 1 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

Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. We find evidence that the network has learned many object classes that play crucial roles in classifying scene classes. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes. By analyzing changes made when small sets of units are activated or deactivated, we find that objects can be added and removed from the output scenes while adapting to the context. Finally, we apply our analytic framework to understanding adversarial attacks and to semantic image editing.

For agents

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

get_harvested_code_for_paper("2009.05041")
get_code_for_paper("2009.05041")
have("2009.05041")

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

curl https://syntology.ai/api/ran/2009.05041.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.05041.svg)](https://syntology.ai/paper/2009.05041)

Connect an agent — have() is free.