Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 4821 in Layer 33

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.5583. Min Act: -0.1700

Data Index: 7608901 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.5270. Min Act: -0.1700

Data Index: 4890184 (Open Web Text)

Max Activating Token Index: 609

Text #2

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.4645. Min Act: -0.1700

Data Index: 3829253 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.3083. Min Act: -0.1700

Data Index: 7109065 (Open Web Text)

Max Activating Token Index: 674

Text #4

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.2770. Min Act: -0.1700

Data Index: 1274705 (Open Web Text)

Max Activating Token Index: 637

Text #5

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.2458. Min Act: -0.1700

Data Index: 7283820 (Open Web Text)

Max Activating Token Index: 231

Text #6

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.2770. Min Act: -0.1700

Data Index: 8532412 (Open Web Text)

Max Activating Token Index: 239

Text #7

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.2145. Min Act: -0.1700

Data Index: 4120459 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 370264 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1833. Min Act: -0.1700

Data Index: 7394330 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 3916897 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 6225907 (Open Web Text)

Max Activating Token Index: 337

Text #12

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 7652819 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 2460856 (Open Web Text)

Max Activating Token Index: 720

Text #14

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1833. Min Act: -0.1700

Data Index: 4580278 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 8449551 (Open Web Text)

Max Activating Token Index: 766

Text #16

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1208. Min Act: -0.1700

Data Index: 3425677 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1520. Min Act: -0.1700

Data Index: 1479873 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1208. Min Act: -0.1700

Data Index: 2073127 (Open Web Text)

Max Activating Token Index: 283

Text #19

Max Range: 7.5583. Min Range: -7.5583

Max Act: 7.1208. Min Act: -0.1700

Data Index: 3258853 (Open Web Text)

Max Activating Token Index: 196