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

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

Neuron 4286 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0002

Data Index: 948334 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0293. Min Act: -0.0002

Data Index: 210529 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0293. Min Act: -0.0002

Data Index: 508856 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0292. Min Act: -0.0002

Data Index: 69452 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1319973 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1114747 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0291. Min Act: -0.0002

Data Index: 210488 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1275313 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0280. Min Act: -0.0002

Data Index: 817830 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0280. Min Act: -0.0002

Data Index: 268406 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0281. Min Act: -0.0002

Data Index: 613214 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0281. Min Act: -0.0002

Data Index: 144297 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0274. Min Act: -0.0002

Data Index: 607312 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1529640 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0272. Min Act: -0.0002

Data Index: 676663 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0002

Data Index: 339697 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0274. Min Act: -0.0002

Data Index: 390702 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1251004 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0268. Min Act: -0.0002

Data Index: 884198 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0268. Min Act: -0.0002

Data Index: 266485 (C4 (Web Text))

Max Activating Token Index: 791