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

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

Neuron 2063 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0233. Min Act: -0.0004

Data Index: 397701 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0235. Min Act: -0.0004

Data Index: 78490 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0004

Data Index: 26786 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1104597 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1257780 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0220. Min Act: -0.0004

Data Index: 20727 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0210. Min Act: -0.0004

Data Index: 1012624 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0204. Min Act: -0.0004

Data Index: 42439 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0201. Min Act: -0.0004

Data Index: 176215 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0218. Min Act: -0.0004

Data Index: 627099 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0219. Min Act: -0.0004

Data Index: 168962 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0204. Min Act: -0.0004

Data Index: 438623 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0211. Min Act: -0.0004

Data Index: 651458 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0210. Min Act: -0.0004

Data Index: 940429 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0214. Min Act: -0.0004

Data Index: 783996 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0184. Min Act: -0.0004

Data Index: 338795 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0198. Min Act: -0.0004

Data Index: 355966 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0198. Min Act: -0.0004

Data Index: 1350441 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1144970 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1286540 (C4 (Web Text))

Max Activating Token Index: 912