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

Dataset: Open Web Text

Neuron 288 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: 5.0772. Min Range: -5.0772

Max Act: 5.0772. Min Act: -0.1700

Data Index: 1402821 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 5.0772. Min Range: -5.0772

Max Act: 5.0548. Min Act: -0.1700

Data Index: 6444878 (Open Web Text)

Max Activating Token Index: 279

Text #2

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9603. Min Act: -0.1700

Data Index: 2357711 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9299. Min Act: -0.1700

Data Index: 562222 (Open Web Text)

Max Activating Token Index: 810

Text #4

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9319. Min Act: -0.1700

Data Index: 7045679 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9053. Min Act: -0.1700

Data Index: 571009 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9310. Min Act: -0.1700

Data Index: 5669315 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9502. Min Act: -0.1700

Data Index: 195886 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9704. Min Act: -0.1700

Data Index: 382459 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9437. Min Act: -0.1700

Data Index: 3726568 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.8761. Min Act: -0.1700

Data Index: 6357007 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9055. Min Act: -0.1700

Data Index: 7100991 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9034. Min Act: -0.1700

Data Index: 6750541 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.8744. Min Act: -0.1700

Data Index: 6419366 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9072. Min Act: -0.1700

Data Index: 3643467 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9104. Min Act: -0.1700

Data Index: 4942395 (Open Web Text)

Max Activating Token Index: 473

Text #16

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9144. Min Act: -0.1700

Data Index: 3561182 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9228. Min Act: -0.1700

Data Index: 5443827 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9295. Min Act: -0.1700

Data Index: 3207894 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 5.0772. Min Range: -5.0772

Max Act: 4.9508. Min Act: -0.1700

Data Index: 5155716 (Open Web Text)

Max Activating Token Index: 768