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

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

Neuron 2024 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0002

Data Index: 600528 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0217. Min Act: -0.0002

Data Index: 100025 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0204. Min Act: -0.0002

Data Index: 687026 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0205. Min Act: -0.0002

Data Index: 132820 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0206. Min Act: -0.0002

Data Index: 146902 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1593341 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1399178 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1264785 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0195. Min Act: -0.0002

Data Index: 752611 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0193. Min Act: -0.0002

Data Index: 195027 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1108747 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0193. Min Act: -0.0002

Data Index: 421737 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0189. Min Act: -0.0002

Data Index: 946086 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1600578 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0187. Min Act: -0.0002

Data Index: 483186 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0186. Min Act: -0.0002

Data Index: 227622 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0184. Min Act: -0.0002

Data Index: 620370 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0183. Min Act: -0.0002

Data Index: 69978 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0182. Min Act: -0.0002

Data Index: 950458 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0180. Min Act: -0.0002

Data Index: 125814 (C4 (Web Text))

Max Activating Token Index: 647