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

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

Neuron 1534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1981. Min Act: -0.0002

Data Index: 1089079 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1808. Min Act: -0.0002

Data Index: 865618 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1678. Min Act: -0.0002

Data Index: 198794 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1559. Min Act: -0.0002

Data Index: 304598 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1315. Min Act: -0.0002

Data Index: 245892 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1336. Min Act: -0.0002

Data Index: 180772 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1275. Min Act: -0.0002

Data Index: 837861 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1264. Min Act: -0.0002

Data Index: 608305 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1246. Min Act: -0.0002

Data Index: 264726 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1199. Min Act: -0.0002

Data Index: 905994 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1238. Min Act: -0.0002

Data Index: 503335 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1232. Min Act: -0.0002

Data Index: 381903 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1231. Min Act: -0.0002

Data Index: 375481 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1001155 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1128. Min Act: -0.0002

Data Index: 74240 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1254. Min Act: -0.0002

Data Index: 519470 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1121. Min Act: -0.0002

Data Index: 98618 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1214. Min Act: -0.0002

Data Index: 493092 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1149. Min Act: -0.0002

Data Index: 908886 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1128. Min Act: -0.0002

Data Index: 827221 (C4 (Web Text))

Max Activating Token Index: 317