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

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

Neuron 60 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0002

Data Index: 530291 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0184. Min Act: -0.0002

Data Index: 725922 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0001

Data Index: 944092 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0153. Min Act: -0.0002

Data Index: 695860 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1396713 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1241027 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0001

Data Index: 468375 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1099892 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0152. Min Act: -0.0002

Data Index: 656382 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1124084 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0001

Data Index: 993001 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0149. Min Act: -0.0002

Data Index: 448654 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0001

Data Index: 1528424 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0001

Data Index: 1065388 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0002

Data Index: 976834 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0146. Min Act: -0.0001

Data Index: 304097 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1382185 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0152. Min Act: -0.0001

Data Index: 696056 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1275018 (C4 (Web Text))

Max Activating Token Index: 43