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

Dataset: Open Web Text

Neuron 2367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.6343. Min Act: 0.0128

Data Index: 2517076 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.5779. Min Act: -0.0340

Data Index: 6203447 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.5508. Min Act: 0.3339

Data Index: 8752171 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.5395. Min Act: 0.2596

Data Index: 3812227 (Open Web Text)

Max Activating Token Index: 103

Text #4

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.5433. Min Act: 1.6190

Data Index: 4860370 (Open Web Text)

Max Activating Token Index: 208

Text #5

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.5409. Min Act: -0.0360

Data Index: 6578716 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.5267. Min Act: 0.1280

Data Index: 5304010 (Open Web Text)

Max Activating Token Index: 806

Text #7

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4851. Min Act: -0.1316

Data Index: 8001211 (Open Web Text)

Max Activating Token Index: 89

Text #8

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4813. Min Act: 0.3697

Data Index: 5448284 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4679. Min Act: -0.0805

Data Index: 1609536 (Open Web Text)

Max Activating Token Index: 171

Text #10

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4819. Min Act: -0.1700

Data Index: 6589247 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4834. Min Act: 0.6391

Data Index: 3674045 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4338. Min Act: 0.0541

Data Index: 3968399 (Open Web Text)

Max Activating Token Index: 926

Text #13

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4587. Min Act: 0.0123

Data Index: 3549836 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4556. Min Act: -0.0078

Data Index: 6469065 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4611. Min Act: 0.1074

Data Index: 4864793 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4631. Min Act: 1.6190

Data Index: 3123337 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4466. Min Act: 0.3578

Data Index: 4776609 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4465. Min Act: 0.1754

Data Index: 3098542 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 5.6343. Min Range: -5.6343

Max Act: 5.4620. Min Act: 0.3568

Data Index: 432595 (Open Web Text)

Max Activating Token Index: 773