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

Dataset: Open Web Text

Neuron 966 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: 4.9543. Min Range: -4.9543

Max Act: 4.9543. Min Act: -0.1700

Data Index: 1086268 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.8093. Min Act: -0.1700

Data Index: 6099979 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.8193. Min Act: -0.1700

Data Index: 3338249 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.9253. Min Act: -0.1700

Data Index: 8775249 (Open Web Text)

Max Activating Token Index: 305

Text #4

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.7833. Min Act: -0.1700

Data Index: 7025580 (Open Web Text)

Max Activating Token Index: 877

Text #5

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.7750. Min Act: -0.1700

Data Index: 4522635 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.7801. Min Act: -0.1700

Data Index: 4206976 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.7163. Min Act: -0.1700

Data Index: 7895494 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.7077. Min Act: -0.1700

Data Index: 5683664 (Open Web Text)

Max Activating Token Index: 727

Text #9

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6692. Min Act: -0.1700

Data Index: 7016147 (Open Web Text)

Max Activating Token Index: 154

Text #10

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6473. Min Act: -0.1700

Data Index: 3876629 (Open Web Text)

Max Activating Token Index: 974

Text #11

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6297. Min Act: -0.1700

Data Index: 1608868 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6183. Min Act: -0.1700

Data Index: 4520456 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.5971. Min Act: -0.1700

Data Index: 112676 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6349. Min Act: -0.1700

Data Index: 3343387 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6131. Min Act: -0.1700

Data Index: 3278234 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6329. Min Act: -0.1700

Data Index: 1670705 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.5614. Min Act: -0.1700

Data Index: 3321727 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.6493. Min Act: -0.1700

Data Index: 3459757 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 4.9543. Min Range: -4.9543

Max Act: 4.5700. Min Act: -0.1700

Data Index: 5253813 (Open Web Text)

Max Activating Token Index: 17