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

Dataset: Open Web Text

Neuron 1292 in Layer 1

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: 5.7021. Min Range: -5.7021

Max Act: 5.6647. Min Act: -0.1700

Data Index: 345445 (Open Web Text)

Max Activating Token Index: 260

Text #1

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.7021. Min Act: -0.1700

Data Index: 3852527 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6397. Min Act: -0.1700

Data Index: 1406878 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6678. Min Act: -0.1700

Data Index: 8045800 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6392. Min Act: -0.1700

Data Index: 7972745 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6343. Min Act: -0.1700

Data Index: 7830101 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6417. Min Act: -0.1700

Data Index: 3432821 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6515. Min Act: -0.1700

Data Index: 2274013 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6410. Min Act: -0.1700

Data Index: 7811701 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6615. Min Act: -0.1700

Data Index: 7268261 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6422. Min Act: -0.1700

Data Index: 5868187 (Open Web Text)

Max Activating Token Index: 806

Text #11

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6514. Min Act: -0.1700

Data Index: 5564192 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6437. Min Act: -0.1700

Data Index: 4374972 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6306. Min Act: -0.1700

Data Index: 3902104 (Open Web Text)

Max Activating Token Index: 926

Text #14

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6369. Min Act: -0.1700

Data Index: 1465814 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6156. Min Act: -0.1700

Data Index: 2608853 (Open Web Text)

Max Activating Token Index: 615

Text #16

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.5988. Min Act: -0.1700

Data Index: 1467302 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6181. Min Act: -0.1700

Data Index: 2792218 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.5868. Min Act: -0.1700

Data Index: 3289529 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 5.7021. Min Range: -5.7021

Max Act: 5.6124. Min Act: -0.1700

Data Index: 788013 (Open Web Text)

Max Activating Token Index: 37