Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.4565. Min Act: -0.0000

Data Index: 91779 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.3102. Min Act: -0.0000

Data Index: 778392 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.3061. Min Act: -0.0000

Data Index: 339612 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.1650. Min Act: -0.0000

Data Index: 1205915 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.2347. Min Act: -0.0000

Data Index: 877998 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.1250. Min Act: -0.0000

Data Index: 46989 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.1172. Min Act: -0.0000

Data Index: 1091627 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.0793. Min Act: -0.0000

Data Index: 55626 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.0513. Min Act: -0.0000

Data Index: 1047907 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.9480. Min Act: -0.0000

Data Index: 1161486 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.0385. Min Act: -0.0000

Data Index: 168934 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 2.4565. Min Range: -2.4565

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1125416 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.8178. Min Act: -0.0000

Data Index: 711483 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.8165. Min Act: -0.0000

Data Index: 567673 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.8060. Min Act: -0.0000

Data Index: 169653 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.8698. Min Act: -0.0000

Data Index: 871262 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.9751. Min Act: -0.0001

Data Index: 459611 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.7572. Min Act: -0.0000

Data Index: 933068 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.8875. Min Act: -0.0000

Data Index: 545309 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 2.4565. Min Range: -2.4565

Max Act: 1.8135. Min Act: -0.0000

Data Index: 353963 (C4 (Web Text))

Max Activating Token Index: 650