Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 877 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1213817 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1602152 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1496976 (Python Code)

Max Activating Token Index: 483

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1525911 (Python Code)

Max Activating Token Index: 606

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1386419 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0197. Min Act: -0.0006

Data Index: 741414 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1620244 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1543587 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0006

Data Index: 232691 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0188. Min Act: -0.0006

Data Index: 48546 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0188. Min Act: -0.0005

Data Index: 932777 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1560599 (Python Code)

Max Activating Token Index: 952

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1450972 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0199. Min Act: -0.0006

Data Index: 403568 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1399642 (Python Code)

Max Activating Token Index: 637

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0194. Min Act: -0.0006

Data Index: 473454 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0189. Min Act: -0.0006

Data Index: 460931 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1494001 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1603901 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0191. Min Act: -0.0006

Data Index: 177206 (C4 (Web Text))

Max Activating Token Index: 562