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

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

Neuron 1485 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: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0002

Data Index: 126505 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0288. Min Act: -0.0003

Data Index: 405425 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0235. Min Act: -0.0002

Data Index: 630265 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1302320 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0289. Min Act: -0.0002

Data Index: 719617 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0233. Min Act: -0.0002

Data Index: 339306 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0276. Min Act: -0.0002

Data Index: 910588 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1128214 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0242. Min Act: -0.0002

Data Index: 51159 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0201. Min Act: -0.0002

Data Index: 117769 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0248. Min Act: -0.0003

Data Index: 833575 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1157605 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1240292 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1648561 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1656486 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1182682 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1643146 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1640867 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1372434 (Python Code)

Max Activating Token Index: 758

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1574132 (Python Code)

Max Activating Token Index: 326