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

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

Neuron 5181 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.8440. Min Act: -0.0000

Data Index: 50614 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.6276. Min Act: -0.0000

Data Index: 902610 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1144636 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5588. Min Act: -0.0000

Data Index: 856232 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4504. Min Act: -0.0000

Data Index: 411905 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3514. Min Act: -0.0000

Data Index: 446285 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1337263 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3278. Min Act: -0.0000

Data Index: 992637 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4121. Min Act: -0.0000

Data Index: 126205 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4226. Min Act: -0.0000

Data Index: 81903 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1359073 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1128045 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4143. Min Act: -0.0000

Data Index: 504936 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4927. Min Act: -0.0000

Data Index: 600612 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3659. Min Act: -0.0000

Data Index: 922191 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.2646. Min Act: -0.0000

Data Index: 752187 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3311. Min Act: -0.0000

Data Index: 808079 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1269926 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3924. Min Act: -0.0000

Data Index: 1358976 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3879. Min Act: -0.0000

Data Index: 837975 (C4 (Web Text))

Max Activating Token Index: 549