Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1373 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.8534. Min Act: -0.1700

Data Index: 621900 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.9159. Min Act: -0.1700

Data Index: 147555 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.8847. Min Act: -0.1700

Data Index: 592005 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.8847. Min Act: -0.1700

Data Index: 625037 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.8222. Min Act: -0.1700

Data Index: 96759 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7909. Min Act: -0.1700

Data Index: 602477 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7284. Min Act: -0.1700

Data Index: 85308 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6659. Min Act: -0.1700

Data Index: 647405 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7597. Min Act: -0.1700

Data Index: 533399 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7909. Min Act: -0.1700

Data Index: 288784 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7597. Min Act: -0.1700

Data Index: 472661 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7284. Min Act: -0.1700

Data Index: 398 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7597. Min Act: -0.1700

Data Index: 892541 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6659. Min Act: -0.1700

Data Index: 243187 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6972. Min Act: -0.1700

Data Index: 530424 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6972. Min Act: -0.1700

Data Index: 198629 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.7284. Min Act: -0.1700

Data Index: 168706 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6347. Min Act: -0.1700

Data Index: 758485 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6659. Min Act: -0.1700

Data Index: 524111 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.9159. Min Range: -5.9159

Max Act: 5.6034. Min Act: -0.1700

Data Index: 1547870 (Python Code)

Max Activating Token Index: 857