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

Dataset: Open Web Text

Neuron 2986 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: 3.7498. Min Range: -3.7498

Max Act: 3.7461. Min Act: -0.1700

Data Index: 602751 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7498. Min Act: -0.1700

Data Index: 5495784 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7405. Min Act: -0.1700

Data Index: 7464645 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7208. Min Act: -0.1700

Data Index: 4789928 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7180. Min Act: -0.1700

Data Index: 5223346 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7074. Min Act: -0.1700

Data Index: 4646245 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7080. Min Act: -0.1700

Data Index: 6305923 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.7264. Min Act: -0.1700

Data Index: 3664302 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6353. Min Act: -0.1700

Data Index: 2195774 (Open Web Text)

Max Activating Token Index: 420

Text #9

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6549. Min Act: -0.1700

Data Index: 1541300 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6615. Min Act: -0.1700

Data Index: 8125342 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6743. Min Act: -0.1700

Data Index: 541109 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6754. Min Act: -0.1700

Data Index: 7998959 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6423. Min Act: -0.1700

Data Index: 4646244 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.5955. Min Act: -0.1700

Data Index: 5639495 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6268. Min Act: -0.1700

Data Index: 6205192 (Open Web Text)

Max Activating Token Index: 503

Text #16

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6286. Min Act: -0.1700

Data Index: 2695744 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6224. Min Act: -0.1700

Data Index: 4342705 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6257. Min Act: -0.1700

Data Index: 6558736 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.7498. Min Range: -3.7498

Max Act: 3.6184. Min Act: -0.1700

Data Index: 846458 (Open Web Text)

Max Activating Token Index: 9