Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 998 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0006

Data Index: 297382 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1172350 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0200. Min Act: -0.0006

Data Index: 591002 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0204. Min Act: -0.0006

Data Index: 554929 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1219984 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0207. Min Act: -0.0006

Data Index: 933676 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1042783 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0182. Min Act: -0.0006

Data Index: 813276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1533020 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1487397 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0186. Min Act: -0.0006

Data Index: 90263 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0186. Min Act: -0.0006

Data Index: 478367 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1533906 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0191. Min Act: -0.0006

Data Index: 628966 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1477055 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0190. Min Act: -0.0006

Data Index: 98152 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0181. Min Act: -0.0006

Data Index: 771599 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1381730 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0184. Min Act: -0.0006

Data Index: 370920 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1622618 (Python Code)

Max Activating Token Index: 743