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

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

Neuron 1708 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1024394 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0311. Min Act: -0.0003

Data Index: 746188 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1146106 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1288913 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0269. Min Act: -0.0002

Data Index: 862848 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0270. Min Act: -0.0002

Data Index: 389736 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0258. Min Act: -0.0003

Data Index: 602045 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1213481 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1072450 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1206101 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1328641 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1355886 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1025544 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1334574 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0230. Min Act: -0.0002

Data Index: 554479 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0233. Min Act: -0.0002

Data Index: 590158 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0229. Min Act: -0.0003

Data Index: 228728 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1627921 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0226. Min Act: -0.0002

Data Index: 427097 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0221. Min Act: -0.0003

Data Index: 164438 (C4 (Web Text))

Max Activating Token Index: 319