Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3136 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0003

Data Index: 298617 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1350715 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0295. Min Act: -0.0004

Data Index: 868265 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0285. Min Act: -0.0003

Data Index: 991623 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0274. Min Act: -0.0003

Data Index: 2640 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0287. Min Act: -0.0003

Data Index: 278189 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0281. Min Act: -0.0003

Data Index: 958706 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0263. Min Act: -0.0003

Data Index: 105223 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0273. Min Act: -0.0003

Data Index: 229256 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0276. Min Act: -0.0003

Data Index: 624022 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0263. Min Act: -0.0003

Data Index: 673948 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0248. Min Act: -0.0003

Data Index: 59723 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0253. Min Act: -0.0003

Data Index: 799529 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0259. Min Act: -0.0003

Data Index: 956314 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1240811 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0255. Min Act: -0.0003

Data Index: 729304 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0239. Min Act: -0.0003

Data Index: 531335 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1364299 (Python Code)

Max Activating Token Index: 643

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1007536 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1053720 (C4 (Web Text))

Max Activating Token Index: 816