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

Dataset: Open Web Text

Neuron 848 in Layer 4

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: 5.1283. Min Range: -5.1283

Max Act: 5.1283. Min Act: -0.1700

Data Index: 5076418 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.9902. Min Act: -0.1700

Data Index: 4697523 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.9858. Min Act: -0.1700

Data Index: 5820598 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.7396. Min Act: -0.1700

Data Index: 6804317 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6892. Min Act: -0.1700

Data Index: 5947150 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6424. Min Act: -0.1700

Data Index: 6035873 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6920. Min Act: -0.1700

Data Index: 8572015 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6923. Min Act: -0.1700

Data Index: 5208374 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6671. Min Act: -0.1700

Data Index: 5665679 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6585. Min Act: -0.1700

Data Index: 4219456 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6082. Min Act: -0.1700

Data Index: 8261113 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6214. Min Act: -0.1700

Data Index: 4516624 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6322. Min Act: -0.1700

Data Index: 2502836 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6323. Min Act: -0.1700

Data Index: 1930155 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.5897. Min Act: -0.1700

Data Index: 3501232 (Open Web Text)

Max Activating Token Index: 493

Text #15

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6034. Min Act: -0.1700

Data Index: 6766409 (Open Web Text)

Max Activating Token Index: 111

Text #16

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.6283. Min Act: -0.1700

Data Index: 4674694 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.5579. Min Act: -0.1700

Data Index: 4474502 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.5759. Min Act: -0.1700

Data Index: 2668982 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 5.1283. Min Range: -5.1283

Max Act: 4.5959. Min Act: -0.1700

Data Index: 7005934 (Open Web Text)

Max Activating Token Index: 150