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

Dataset: Open Web Text

Neuron 566 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: 1.3528. Min Range: -1.3528

Max Act: 1.3485. Min Act: -0.1700

Data Index: 3982376 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3449. Min Act: -0.1664

Data Index: 6141901 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3528. Min Act: -0.1700

Data Index: 8053732 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3432. Min Act: -0.1700

Data Index: 2656374 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3421. Min Act: -0.1700

Data Index: 3941330 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3381. Min Act: -0.1700

Data Index: 5574373 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3310. Min Act: -0.1687

Data Index: 5193541 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3352. Min Act: -0.1698

Data Index: 7852238 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3199. Min Act: -0.1700

Data Index: 6977961 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3173. Min Act: -0.1695

Data Index: 3020980 (Open Web Text)

Max Activating Token Index: 905

Text #10

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3241. Min Act: -0.1669

Data Index: 6737916 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3276. Min Act: -0.1683

Data Index: 149436 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3115. Min Act: -0.1700

Data Index: 4610797 (Open Web Text)

Max Activating Token Index: 227

Text #13

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3129. Min Act: -0.1699

Data Index: 8134060 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3041. Min Act: -0.1700

Data Index: 8580508 (Open Web Text)

Max Activating Token Index: 680

Text #15

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3072. Min Act: -0.1667

Data Index: 7512613 (Open Web Text)

Max Activating Token Index: 246

Text #16

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3089. Min Act: -0.1699

Data Index: 5357807 (Open Web Text)

Max Activating Token Index: 351

Text #17

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3016. Min Act: -0.1700

Data Index: 6854256 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3011. Min Act: -0.1700

Data Index: 1884624 (Open Web Text)

Max Activating Token Index: 181

Text #19

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.3072. Min Act: -0.1625

Data Index: 1431116 (Open Web Text)

Max Activating Token Index: 132