Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3082 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1384446 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1400729 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1372067 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1398010 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1518380 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1415930 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0250. Min Act: -0.0003

Data Index: 965274 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0246. Min Act: -0.0003

Data Index: 609212 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1373304 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1479879 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0235. Min Act: -0.0002

Data Index: 963689 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1550013 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1588533 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1457778 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1527073 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1606708 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1337049 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1370093 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1488226 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1459043 (Python Code)

Max Activating Token Index: 624