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

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

Neuron 643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1194881 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1641507 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1647537 (Python Code)

Max Activating Token Index: 71

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1377405 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1621275 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1494348 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1535411 (Python Code)

Max Activating Token Index: 649

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1426855 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0202. Min Act: -0.0003

Data Index: 599550 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1623682 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0176. Min Act: -0.0003

Data Index: 444998 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1108362 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1589570 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1470615 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0182. Min Act: -0.0003

Data Index: 804915 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0183. Min Act: -0.0003

Data Index: 186754 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0180. Min Act: -0.0003

Data Index: 707971 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1489554 (Python Code)

Max Activating Token Index: 390

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0180. Min Act: -0.0003

Data Index: 26902 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1541107 (Python Code)

Max Activating Token Index: 223