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

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

Neuron 683 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: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0006

Data Index: 272412 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0277. Min Act: -0.0006

Data Index: 189403 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0275. Min Act: -0.0006

Data Index: 983682 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0262. Min Act: -0.0006

Data Index: 905671 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0255. Min Act: -0.0006

Data Index: 464034 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0244. Min Act: -0.0006

Data Index: 638396 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1185190 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0260. Min Act: -0.0006

Data Index: 522394 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0245. Min Act: -0.0006

Data Index: 920589 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0238. Min Act: -0.0006

Data Index: 700687 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0232. Min Act: -0.0006

Data Index: 40985 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0242. Min Act: -0.0006

Data Index: 584338 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1130135 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0234. Min Act: -0.0006

Data Index: 611146 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1315298 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0238. Min Act: -0.0006

Data Index: 438105 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0237. Min Act: -0.0006

Data Index: 231657 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0232. Min Act: -0.0006

Data Index: 891349 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0231. Min Act: -0.0006

Data Index: 646832 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1143207 (C4 (Web Text))

Max Activating Token Index: 624