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

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

Neuron 3742 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: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0001

Data Index: 574759 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1029093 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1135734 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1020038 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0186. Min Act: -0.0001

Data Index: 358224 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0186. Min Act: -0.0001

Data Index: 786091 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0181. Min Act: -0.0002

Data Index: 298150 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0176. Min Act: -0.0001

Data Index: 643004 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1117289 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0171. Min Act: -0.0002

Data Index: 685025 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0167. Min Act: -0.0001

Data Index: 42508 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0170. Min Act: -0.0001

Data Index: 520973 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0166. Min Act: -0.0001

Data Index: 713332 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0164. Min Act: -0.0002

Data Index: 438092 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0164. Min Act: -0.0001

Data Index: 265374 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0164. Min Act: -0.0002

Data Index: 640799 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0163. Min Act: -0.0002

Data Index: 592430 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0161. Min Act: -0.0001

Data Index: 127751 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0161. Min Act: -0.0001

Data Index: 263689 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1211744 (C4 (Web Text))

Max Activating Token Index: 984