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

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

Neuron 1910 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1014629 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0383. Min Act: -0.0003

Data Index: 745208 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1187261 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0003

Data Index: 98701 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1247305 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0341. Min Act: -0.0003

Data Index: 650176 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0003

Data Index: 124505 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0333. Min Act: -0.0003

Data Index: 81131 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0340. Min Act: -0.0003

Data Index: 10022 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0003

Data Index: 705473 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1136092 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1167854 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0311. Min Act: -0.0003

Data Index: 226833 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0322. Min Act: -0.0003

Data Index: 827080 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0294. Min Act: -0.0003

Data Index: 339801 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0315. Min Act: -0.0003

Data Index: 677273 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0309. Min Act: -0.0003

Data Index: 979849 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0308. Min Act: -0.0003

Data Index: 994637 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0313. Min Act: -0.0003

Data Index: 363680 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1264144 (C4 (Web Text))

Max Activating Token Index: 977