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

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

Neuron 4658 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: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0003

Data Index: 305702 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0304. Min Act: -0.0003

Data Index: 371219 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1308201 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1461709 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0264. Min Act: -0.0003

Data Index: 75812 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0242. Min Act: -0.0002

Data Index: 228421 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0258. Min Act: -0.0003

Data Index: 233840 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1332361 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1117434 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0235. Min Act: -0.0003

Data Index: 34443 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1436513 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0233. Min Act: -0.0003

Data Index: 997132 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1294378 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1515593 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0242. Min Act: -0.0003

Data Index: 250204 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1034434 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1491008 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1419524 (Python Code)

Max Activating Token Index: 238

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1375448 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1539407 (Python Code)

Max Activating Token Index: 427