Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5280 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3962. Min Range: -1.3962

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1320820 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.3962. Min Range: -1.3962

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1267079 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 1.3962. Min Range: -1.3962

Max Act: 1.2139. Min Act: -0.0000

Data Index: 929567 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.3962. Min Range: -1.3962

Max Act: 1.3031. Min Act: -0.0000

Data Index: 837249 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9439. Min Act: -0.0000

Data Index: 778023 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9812. Min Act: -0.0000

Data Index: 38353 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 1.3962. Min Range: -1.3962

Max Act: 1.0074. Min Act: -0.0000

Data Index: 506107 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1037293 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9466. Min Act: -0.0000

Data Index: 487283 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.3962. Min Range: -1.3962

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1195065 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1166532 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9339. Min Act: -0.0000

Data Index: 381302 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9057. Min Act: -0.0000

Data Index: 788466 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1141010 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1189006 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1197102 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.8264. Min Act: -0.0000

Data Index: 782107 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.8430. Min Act: -0.0000

Data Index: 731010 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.9166. Min Act: -0.0000

Data Index: 99773 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.3962. Min Range: -1.3962

Max Act: 0.8352. Min Act: -0.0000

Data Index: 432232 (C4 (Web Text))

Max Activating Token Index: 998