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

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

Neuron 90 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: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0004

Data Index: 1211716 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0173. Min Act: -0.0003

Data Index: 240348 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1188965 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0168. Min Act: -0.0004

Data Index: 586866 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0171. Min Act: -0.0003

Data Index: 401005 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1595037 (Python Code)

Max Activating Token Index: 828

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0167. Min Act: -0.0004

Data Index: 1150253 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0166. Min Act: -0.0003

Data Index: 566719 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1264999 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0165. Min Act: -0.0004

Data Index: 520673 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0160. Min Act: -0.0004

Data Index: 216780 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0162. Min Act: -0.0004

Data Index: 728997 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0162. Min Act: -0.0004

Data Index: 563296 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1364231 (Python Code)

Max Activating Token Index: 353

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1065271 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1013159 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0157. Min Act: -0.0004

Data Index: 435536 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1188962 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1151525 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0153. Min Act: -0.0004

Data Index: 533317 (C4 (Web Text))

Max Activating Token Index: 273