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

Dataset: Open Web Text

Neuron 638 in Layer 5

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: 4.9834. Min Range: -4.9834

Max Act: 4.9475. Min Act: -0.1700

Data Index: 420013 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9834. Min Act: -0.1700

Data Index: 7740231 (Open Web Text)

Max Activating Token Index: 662

Text #2

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9294. Min Act: -0.1700

Data Index: 7476368 (Open Web Text)

Max Activating Token Index: 729

Text #3

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9353. Min Act: -0.1700

Data Index: 8564672 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9268. Min Act: -0.1700

Data Index: 7216002 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9116. Min Act: -0.1700

Data Index: 420012 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9430. Min Act: -0.1700

Data Index: 5877348 (Open Web Text)

Max Activating Token Index: 857

Text #7

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9149. Min Act: -0.1700

Data Index: 2186309 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9256. Min Act: -0.1700

Data Index: 871285 (Open Web Text)

Max Activating Token Index: 924

Text #9

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9283. Min Act: -0.1700

Data Index: 871284 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9028. Min Act: -0.1700

Data Index: 8564671 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9070. Min Act: -0.1700

Data Index: 5877350 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9097. Min Act: -0.1700

Data Index: 1575058 (Open Web Text)

Max Activating Token Index: 122

Text #13

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9134. Min Act: -0.1700

Data Index: 2191186 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.8917. Min Act: -0.1700

Data Index: 2191185 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.8764. Min Act: -0.1700

Data Index: 6427330 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9345. Min Act: -0.1700

Data Index: 1575056 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.8808. Min Act: -0.1700

Data Index: 7216001 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9211. Min Act: -0.1700

Data Index: 7476370 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 4.9834. Min Range: -4.9834

Max Act: 4.9030. Min Act: -0.1700

Data Index: 2457870 (Open Web Text)

Max Activating Token Index: 823