Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1253 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1439139 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0187. Min Act: -0.0003

Data Index: 218857 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1641948 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0002

Data Index: 367403 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1647895 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1404655 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1556465 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1050749 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0141. Min Act: -0.0003

Data Index: 112430 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1550359 (Python Code)

Max Activating Token Index: 345

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1497396 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0138. Min Act: -0.0004

Data Index: 629646 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1403010 (Python Code)

Max Activating Token Index: 316

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1406160 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1526887 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1414987 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1444045 (Python Code)

Max Activating Token Index: 349

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1517716 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1390207 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0124. Min Act: -0.0003

Data Index: 616865 (C4 (Web Text))

Max Activating Token Index: 354