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

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

Neuron 5022 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: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0002

Data Index: 784299 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0276. Min Act: -0.0002

Data Index: 26009 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0261. Min Act: -0.0002

Data Index: 187273 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0251. Min Act: -0.0002

Data Index: 389262 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0237. Min Act: -0.0002

Data Index: 472153 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0227. Min Act: -0.0002

Data Index: 146500 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0227. Min Act: -0.0002

Data Index: 447506 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0232. Min Act: -0.0002

Data Index: 37305 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1092603 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0215. Min Act: -0.0002

Data Index: 45200 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0206. Min Act: -0.0002

Data Index: 694565 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1065656 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1115683 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1005180 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0219. Min Act: -0.0002

Data Index: 191272 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0202. Min Act: -0.0002

Data Index: 730299 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0202. Min Act: -0.0002

Data Index: 950022 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0209. Min Act: -0.0002

Data Index: 256723 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0212. Min Act: -0.0002

Data Index: 841690 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1038333 (C4 (Web Text))

Max Activating Token Index: 112