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

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

Neuron 153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0001

Data Index: 256287 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0355. Min Act: -0.0001

Data Index: 147297 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0257. Min Act: -0.0001

Data Index: 744024 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1545506 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1324552 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1123868 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0293. Min Act: -0.0001

Data Index: 24343 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0295. Min Act: -0.0001

Data Index: 782124 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1508047 (Python Code)

Max Activating Token Index: 638

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0295. Min Act: -0.0001

Data Index: 357636 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1046499 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0278. Min Act: -0.0001

Data Index: 590888 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0263. Min Act: -0.0001

Data Index: 354398 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0277. Min Act: -0.0001

Data Index: 497968 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0287. Min Act: -0.0001

Data Index: 182045 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0267. Min Act: -0.0001

Data Index: 787614 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0274. Min Act: -0.0001

Data Index: 688070 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1401022 (Python Code)

Max Activating Token Index: 499

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0266. Min Act: -0.0001

Data Index: 289773 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0268. Min Act: -0.0001

Data Index: 926520 (C4 (Web Text))

Max Activating Token Index: 910