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

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

Neuron 700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1615983 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1300995 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0336. Min Act: -0.0003

Data Index: 324213 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1307899 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1264692 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0290. Min Act: -0.0003

Data Index: 622616 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0304. Min Act: -0.0003

Data Index: 372857 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0285. Min Act: -0.0003

Data Index: 713804 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1132331 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1106797 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1263214 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0274. Min Act: -0.0003

Data Index: 495481 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0280. Min Act: -0.0003

Data Index: 479454 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0267. Min Act: -0.0003

Data Index: 861964 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1267543 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0262. Min Act: -0.0003

Data Index: 892818 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0273. Min Act: -0.0003

Data Index: 505912 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0280. Min Act: -0.0003

Data Index: 630308 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1314557 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0259. Min Act: -0.0003

Data Index: 871973 (C4 (Web Text))

Max Activating Token Index: 478