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

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

Neuron 2068 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: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0004

Data Index: 35076 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0233. Min Act: -0.0004

Data Index: 81400 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0220. Min Act: -0.0004

Data Index: 3167 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1056073 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0222. Min Act: -0.0004

Data Index: 1236020 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1146440 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0226. Min Act: -0.0004

Data Index: 906820 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0221. Min Act: -0.0004

Data Index: 767915 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0234. Min Act: -0.0004

Data Index: 742402 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0224. Min Act: -0.0004

Data Index: 1179942 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0206. Min Act: -0.0004

Data Index: 367685 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0224. Min Act: -0.0004

Data Index: 1032528 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0215. Min Act: -0.0004

Data Index: 140746 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0204. Min Act: -0.0004

Data Index: 1185591 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0203. Min Act: -0.0004

Data Index: 715529 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0214. Min Act: -0.0004

Data Index: 781504 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0210. Min Act: -0.0004

Data Index: 956062 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1296079 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1176680 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0186. Min Act: -0.0004

Data Index: 1055761 (C4 (Web Text))

Max Activating Token Index: 657