Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 886 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1053336 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0203. Min Act: -0.0005

Data Index: 79311 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0203. Min Act: -0.0005

Data Index: 695625 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0189. Min Act: -0.0005

Data Index: 928701 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0199. Min Act: -0.0005

Data Index: 652327 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0187. Min Act: -0.0005

Data Index: 742500 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0188. Min Act: -0.0005

Data Index: 933991 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0193. Min Act: -0.0005

Data Index: 873905 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0180. Min Act: -0.0005

Data Index: 244230 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0005

Data Index: 84644 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0178. Min Act: -0.0005

Data Index: 396833 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0181. Min Act: -0.0005

Data Index: 143925 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0180. Min Act: -0.0005

Data Index: 1089437 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0177. Min Act: -0.0005

Data Index: 73818 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0169. Min Act: -0.0005

Data Index: 571146 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0005

Data Index: 99458 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1278093 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0177. Min Act: -0.0005

Data Index: 500966 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0165. Min Act: -0.0005

Data Index: 487808 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1053805 (C4 (Web Text))

Max Activating Token Index: 927