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

Dataset: Open Web Text

Neuron 2912 in Layer 6

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: 3.9866. Min Range: -3.9866

Max Act: 3.9866. Min Act: -0.1700

Data Index: 3275554 (Open Web Text)

Max Activating Token Index: 850

Text #1

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.9502. Min Act: -0.1700

Data Index: 5796109 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.8674. Min Act: -0.1700

Data Index: 1853130 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.8341. Min Act: -0.1700

Data Index: 4546326 (Open Web Text)

Max Activating Token Index: 259

Text #4

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.8273. Min Act: -0.1700

Data Index: 8408231 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.8226. Min Act: -0.1700

Data Index: 734759 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.8196. Min Act: -0.1700

Data Index: 2087220 (Open Web Text)

Max Activating Token Index: 757

Text #7

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7585. Min Act: -0.1700

Data Index: 4264152 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7775. Min Act: -0.1700

Data Index: 7983694 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.8019. Min Act: -0.1700

Data Index: 4923020 (Open Web Text)

Max Activating Token Index: 156

Text #10

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7685. Min Act: -0.1700

Data Index: 5258210 (Open Web Text)

Max Activating Token Index: 763

Text #11

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7602. Min Act: -0.1700

Data Index: 5464345 (Open Web Text)

Max Activating Token Index: 128

Text #12

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7461. Min Act: -0.1700

Data Index: 3812096 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7593. Min Act: -0.1700

Data Index: 1147898 (Open Web Text)

Max Activating Token Index: 213

Text #14

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7538. Min Act: -0.1700

Data Index: 8705517 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7192. Min Act: -0.1700

Data Index: 1004403 (Open Web Text)

Max Activating Token Index: 880

Text #16

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7278. Min Act: -0.1700

Data Index: 5323590 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7284. Min Act: -0.1700

Data Index: 2149917 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7291. Min Act: -0.1700

Data Index: 4382568 (Open Web Text)

Max Activating Token Index: 866

Text #19

Max Range: 3.9866. Min Range: -3.9866

Max Act: 3.7173. Min Act: -0.1700

Data Index: 2189305 (Open Web Text)

Max Activating Token Index: 921