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

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

Neuron 3934 in Layer 3

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: -0.0001

Data Index: 568407 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0212. Min Act: -0.0001

Data Index: 286436 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0198. Min Act: -0.0001

Data Index: 247818 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1158863 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0173. Min Act: -0.0001

Data Index: 50704 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0180. Min Act: -0.0001

Data Index: 607845 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0183. Min Act: -0.0001

Data Index: 347901 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0183. Min Act: -0.0001

Data Index: 71453 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0168. Min Act: -0.0001

Data Index: 19744 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0181. Min Act: -0.0001

Data Index: 207523 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0178. Min Act: -0.0001

Data Index: 959949 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1122626 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1285052 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1041983 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0146. Min Act: -0.0001

Data Index: 218124 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0156. Min Act: -0.0001

Data Index: 343059 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0163. Min Act: -0.0001

Data Index: 448510 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0152. Min Act: -0.0001

Data Index: 508021 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0152. Min Act: -0.0001

Data Index: 1521360 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0144. Min Act: -0.0001

Data Index: 799370 (C4 (Web Text))

Max Activating Token Index: 562