Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1279403 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1106220 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1225765 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0230. Min Act: -0.0001

Data Index: 246713 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0219. Min Act: -0.0001

Data Index: 953533 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1569478 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0235. Min Act: -0.0001

Data Index: 805356 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1021205 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0201. Min Act: -0.0001

Data Index: 318375 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1214398 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0200. Min Act: -0.0001

Data Index: 479164 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1318990 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1069920 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0190. Min Act: -0.0001

Data Index: 614691 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0200. Min Act: -0.0001

Data Index: 840526 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1564647 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1094795 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0198. Min Act: -0.0001

Data Index: 812726 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0180. Min Act: -0.0001

Data Index: 991526 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0170. Min Act: -0.0001

Data Index: 262890 (C4 (Web Text))

Max Activating Token Index: 592