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

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

Neuron 4594 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0323. Min Act: -0.0002

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0002

Data Index: 262436 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0327. Min Act: -0.0002

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1254115 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0318. Min Act: -0.0002

Data Index: 101653 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0318. Min Act: -0.0002

Data Index: 353837 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1053035 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0002

Data Index: 748736 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1258913 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0291. Min Act: -0.0002

Data Index: 505741 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1008680 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1210242 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1147879 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0250. Min Act: -0.0002

Data Index: 796478 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1311424 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1000734 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0259. Min Act: -0.0002

Data Index: 588123 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1324686 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0242. Min Act: -0.0002

Data Index: 181807 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1064531 (C4 (Web Text))

Max Activating Token Index: 12