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

Dataset: Open Web Text

Neuron 720 in Layer 2

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: 3.6121. Min Range: -3.6121

Max Act: 3.6121. Min Act: -0.1700

Data Index: 3691007 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.6113. Min Act: -0.1700

Data Index: 4601737 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.5927. Min Act: -0.1700

Data Index: 988791 (Open Web Text)

Max Activating Token Index: 747

Text #3

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.5859. Min Act: -0.1700

Data Index: 3264915 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.4627. Min Act: -0.1700

Data Index: 6707975 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.4523. Min Act: -0.1700

Data Index: 2300718 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.4644. Min Act: -0.1700

Data Index: 7272004 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3974. Min Act: -0.1700

Data Index: 4590978 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3704. Min Act: -0.1700

Data Index: 3388593 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3622. Min Act: -0.1700

Data Index: 8696760 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3477. Min Act: -0.1700

Data Index: 1689552 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3353. Min Act: -0.1700

Data Index: 4846530 (Open Web Text)

Max Activating Token Index: 743

Text #12

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3360. Min Act: -0.1700

Data Index: 8156087 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3319. Min Act: -0.1700

Data Index: 773120 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3276. Min Act: -0.1700

Data Index: 8320805 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3303. Min Act: -0.1700

Data Index: 3817322 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3161. Min Act: -0.1700

Data Index: 2248788 (Open Web Text)

Max Activating Token Index: 619

Text #17

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3213. Min Act: -0.1700

Data Index: 6670591 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3141. Min Act: -0.1700

Data Index: 5223768 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3013. Min Act: -0.1700

Data Index: 6239176 (Open Web Text)

Max Activating Token Index: 665