Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1163 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.5436. Min Act: -0.1700

Data Index: 6423054 (Open Web Text)

Max Activating Token Index: 739

Text #1

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.5041. Min Act: -0.1700

Data Index: 287898 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.4177. Min Act: -0.1700

Data Index: 550790 (Open Web Text)

Max Activating Token Index: 892

Text #3

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.4384. Min Act: -0.1700

Data Index: 1337727 (Open Web Text)

Max Activating Token Index: 676

Text #4

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.4287. Min Act: -0.1700

Data Index: 7818753 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3773. Min Act: -0.1700

Data Index: 8201646 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3678. Min Act: -0.1700

Data Index: 1412391 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2980. Min Act: -0.1700

Data Index: 1984414 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3690. Min Act: -0.1700

Data Index: 7839896 (Open Web Text)

Max Activating Token Index: 314

Text #9

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3582. Min Act: -0.1700

Data Index: 1341235 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3471. Min Act: -0.1700

Data Index: 2964297 (Open Web Text)

Max Activating Token Index: 83

Text #11

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3225. Min Act: -0.1700

Data Index: 319865 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2858. Min Act: -0.1700

Data Index: 4672233 (Open Web Text)

Max Activating Token Index: 440

Text #13

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2806. Min Act: -0.1700

Data Index: 2549285 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2323. Min Act: -0.1700

Data Index: 8258726 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2646. Min Act: -0.1700

Data Index: 7842159 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2675. Min Act: -0.1700

Data Index: 3169190 (Open Web Text)

Max Activating Token Index: 915

Text #17

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2921. Min Act: -0.1700

Data Index: 5013017 (Open Web Text)

Max Activating Token Index: 104

Text #18

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.3336. Min Act: -0.1700

Data Index: 3567123 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 3.5436. Min Range: -3.5436

Max Act: 3.2889. Min Act: -0.1700

Data Index: 4116154 (Open Web Text)

Max Activating Token Index: 678