Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3767 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0446. Min Act: -0.0001

Data Index: 139826 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0385. Min Act: -0.0001

Data Index: 245194 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0337. Min Act: -0.0001

Data Index: 577291 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0351. Min Act: -0.0001

Data Index: 355560 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1087065 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0322. Min Act: -0.0001

Data Index: 927566 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0305. Min Act: -0.0001

Data Index: 194653 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1262042 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1037536 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0305. Min Act: -0.0001

Data Index: 114516 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0300. Min Act: -0.0001

Data Index: 590334 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0330. Min Act: -0.0001

Data Index: 133518 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1328198 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1001767 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0273. Min Act: -0.0001

Data Index: 561674 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0290. Min Act: -0.0001

Data Index: 454578 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1292612 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1253693 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0254. Min Act: -0.0001

Data Index: 284466 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.0446. Min Range: -0.0446

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1158175 (C4 (Web Text))

Max Activating Token Index: 550