Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4661 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0002

Data Index: 224191 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0302. Min Act: -0.0003

Data Index: 58054 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1025622 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0265. Min Act: -0.0003

Data Index: 541067 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0250. Min Act: -0.0002

Data Index: 38163 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0255. Min Act: -0.0003

Data Index: 760470 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0244. Min Act: -0.0003

Data Index: 829499 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1431505 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1623914 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0232. Min Act: -0.0002

Data Index: 135887 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0236. Min Act: -0.0003

Data Index: 14624 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1416183 (Python Code)

Max Activating Token Index: 332

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0211. Min Act: -0.0003

Data Index: 798738 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0223. Min Act: -0.0002

Data Index: 533332 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0221. Min Act: -0.0003

Data Index: 673273 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0216. Min Act: -0.0003

Data Index: 687063 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1375811 (Python Code)

Max Activating Token Index: 344

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1575985 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0207. Min Act: -0.0003

Data Index: 376570 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0209. Min Act: -0.0003

Data Index: 714729 (C4 (Web Text))

Max Activating Token Index: 925