Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 532 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0004

Data Index: 235144 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0265. Min Act: -0.0004

Data Index: 267185 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0275. Min Act: -0.0004

Data Index: 73081 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1093989 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0242. Min Act: -0.0004

Data Index: 103280 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0271. Min Act: -0.0004

Data Index: 845974 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0255. Min Act: -0.0004

Data Index: 435235 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1071722 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0244. Min Act: -0.0004

Data Index: 597405 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1336600 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0246. Min Act: -0.0004

Data Index: 1097839 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0236. Min Act: -0.0004

Data Index: 148311 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1239193 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0232. Min Act: -0.0004

Data Index: 71012 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1041113 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0213. Min Act: -0.0004

Data Index: 677798 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1296091 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0193. Min Act: -0.0004

Data Index: 29580 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0216. Min Act: -0.0004

Data Index: 797736 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0182. Min Act: -0.0004

Data Index: 1125943 (C4 (Web Text))

Max Activating Token Index: 328