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

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

Neuron 440 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1603743 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0182. Min Act: -0.0003

Data Index: 872841 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0180. Min Act: -0.0002

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1266187 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1570288 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1566145 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0169. Min Act: -0.0003

Data Index: 757080 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0169. Min Act: -0.0003

Data Index: 87953 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0173. Min Act: -0.0003

Data Index: 633144 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0168. Min Act: -0.0003

Data Index: 526899 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0164. Min Act: -0.0003

Data Index: 22145 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0164. Min Act: -0.0003

Data Index: 791644 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0161. Min Act: -0.0003

Data Index: 986342 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0147. Min Act: -0.0003

Data Index: 454535 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0164. Min Act: -0.0003

Data Index: 904586 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1545624 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1166712 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1072215 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0166. Min Act: -0.0003

Data Index: 630386 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1555194 (Python Code)

Max Activating Token Index: 164