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

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

Neuron 3975 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: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0002

Data Index: 6508 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1002149 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0266. Min Act: -0.0003

Data Index: 811812 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0251. Min Act: -0.0003

Data Index: 23703 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0239. Min Act: -0.0003

Data Index: 346476 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1171604 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0235. Min Act: -0.0003

Data Index: 707252 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0230. Min Act: -0.0003

Data Index: 281348 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0219. Min Act: -0.0003

Data Index: 448707 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1326921 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0215. Min Act: -0.0003

Data Index: 230691 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0216. Min Act: -0.0003

Data Index: 449797 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0219. Min Act: -0.0003

Data Index: 244137 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0220. Min Act: -0.0003

Data Index: 612214 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0206. Min Act: -0.0003

Data Index: 983035 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1578102 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1237242 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1448223 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0223. Min Act: -0.0003

Data Index: 694981 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1274043 (C4 (Web Text))

Max Activating Token Index: 986