Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3442 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1121570 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1346421 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0001

Data Index: 366372 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0001

Data Index: 918739 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0194. Min Act: -0.0001

Data Index: 636805 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0186. Min Act: -0.0001

Data Index: 791374 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0184. Min Act: -0.0001

Data Index: 982343 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0153. Min Act: -0.0001

Data Index: 1478767 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0198. Min Act: -0.0001

Data Index: 332679 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1353247 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0166. Min Act: -0.0001

Data Index: 541363 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0170. Min Act: -0.0001

Data Index: 83114 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0155. Min Act: -0.0001

Data Index: 421608 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1157124 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0169. Min Act: -0.0001

Data Index: 806207 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0169. Min Act: -0.0002

Data Index: 504565 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1542004 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0164. Min Act: -0.0001

Data Index: 76781 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0173. Min Act: -0.0001

Data Index: 274678 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0169. Min Act: -0.0001

Data Index: 318307 (C4 (Web Text))

Max Activating Token Index: 422