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

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

Neuron 4613 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.8375. Min Act: -0.0000

Data Index: 243490 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.8110. Min Act: -0.0000

Data Index: 960670 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.8240. Min Act: -0.0000

Data Index: 218479 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1172491 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.7524. Min Act: -0.0000

Data Index: 267861 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.7293. Min Act: -0.0000

Data Index: 586590 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.7198. Min Act: -0.0000

Data Index: 807188 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.7044. Min Act: -0.0000

Data Index: 329406 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1035197 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.6650. Min Act: -0.0000

Data Index: 998911 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1294769 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.6221. Min Act: -0.0000

Data Index: 522589 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.6234. Min Act: -0.0000

Data Index: 556558 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5882. Min Act: -0.0000

Data Index: 579300 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1343759 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5335. Min Act: -0.0000

Data Index: 748719 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5323. Min Act: -0.0000

Data Index: 313166 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5830. Min Act: -0.0000

Data Index: 747428 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5614. Min Act: -0.0000

Data Index: 64672 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.8375. Min Range: -0.8375

Max Act: 0.5596. Min Act: -0.0000

Data Index: 643176 (C4 (Web Text))

Max Activating Token Index: 441