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

Dataset: Open Web Text

Neuron 381 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: 4.4138. Min Range: -4.4138

Max Act: 4.4138. Min Act: -0.1700

Data Index: 5978773 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.3004. Min Act: -0.1700

Data Index: 8011089 (Open Web Text)

Max Activating Token Index: 240

Text #2

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1521. Min Act: -0.1700

Data Index: 3287956 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1948. Min Act: -0.1700

Data Index: 8203886 (Open Web Text)

Max Activating Token Index: 42

Text #4

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1830. Min Act: -0.1700

Data Index: 1845465 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1334. Min Act: -0.1700

Data Index: 6211392 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1403. Min Act: -0.1700

Data Index: 5599600 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1783. Min Act: -0.1700

Data Index: 7994137 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1899. Min Act: -0.1700

Data Index: 2730597 (Open Web Text)

Max Activating Token Index: 622

Text #9

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1535. Min Act: -0.1700

Data Index: 4440695 (Open Web Text)

Max Activating Token Index: 819

Text #10

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1463. Min Act: -0.1700

Data Index: 7740433 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.0882. Min Act: -0.1700

Data Index: 8009610 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.0826. Min Act: -0.1700

Data Index: 6531399 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.0371. Min Act: -0.1700

Data Index: 7807845 (Open Web Text)

Max Activating Token Index: 811

Text #14

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.0904. Min Act: -0.1700

Data Index: 8772570 (Open Web Text)

Max Activating Token Index: 792

Text #15

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.0585. Min Act: -0.1700

Data Index: 3078944 (Open Web Text)

Max Activating Token Index: 877

Text #16

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.0813. Min Act: -0.1700

Data Index: 6761064 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1341. Min Act: -0.1700

Data Index: 6793452 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1128. Min Act: -0.1700

Data Index: 601673 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 4.4138. Min Range: -4.4138

Max Act: 4.1260. Min Act: -0.1700

Data Index: 6915450 (Open Web Text)

Max Activating Token Index: 832