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

Dataset: Open Web Text

Neuron 35 in Layer 4

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: 3.3129. Min Range: -3.3129

Max Act: 3.3129. Min Act: -0.1700

Data Index: 5720260 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2682. Min Act: -0.1700

Data Index: 8175326 (Open Web Text)

Max Activating Token Index: 864

Text #2

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2593. Min Act: -0.1700

Data Index: 5730223 (Open Web Text)

Max Activating Token Index: 1004

Text #3

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2501. Min Act: -0.1700

Data Index: 1527631 (Open Web Text)

Max Activating Token Index: 811

Text #4

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2330. Min Act: -0.1700

Data Index: 6317392 (Open Web Text)

Max Activating Token Index: 985

Text #5

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1942. Min Act: -0.1700

Data Index: 277448 (Open Web Text)

Max Activating Token Index: 860

Text #6

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1595598 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.2181. Min Act: -0.1700

Data Index: 3668587 (Open Web Text)

Max Activating Token Index: 862

Text #8

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1757. Min Act: -0.1700

Data Index: 6020595 (Open Web Text)

Max Activating Token Index: 1013

Text #9

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1306. Min Act: -0.1700

Data Index: 5348500 (Open Web Text)

Max Activating Token Index: 934

Text #10

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1527. Min Act: -0.1700

Data Index: 2535907 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1440. Min Act: -0.1700

Data Index: 6628364 (Open Web Text)

Max Activating Token Index: 885

Text #12

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1338. Min Act: -0.1700

Data Index: 3644471 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1167. Min Act: -0.1700

Data Index: 7721174 (Open Web Text)

Max Activating Token Index: 354

Text #14

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.0837. Min Act: -0.1700

Data Index: 5495974 (Open Web Text)

Max Activating Token Index: 929

Text #15

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1415. Min Act: -0.1700

Data Index: 4544389 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1115. Min Act: -0.1700

Data Index: 3682411 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.1193. Min Act: -0.1700

Data Index: 4700350 (Open Web Text)

Max Activating Token Index: 931

Text #18

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.0902. Min Act: -0.1700

Data Index: 4035980 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 3.3129. Min Range: -3.3129

Max Act: 3.0921. Min Act: -0.1700

Data Index: 7856583 (Open Web Text)

Max Activating Token Index: 292