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

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

Neuron 4050 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: 0.0509. Min Range: -0.0509

Max Act: 0.0509. Min Act: -0.0002

Data Index: 344462 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0427. Min Act: -0.0002

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1118812 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0344. Min Act: -0.0003

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1189296 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0353. Min Act: -0.0002

Data Index: 186230 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0348. Min Act: -0.0003

Data Index: 225080 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1444011 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0340. Min Act: -0.0002

Data Index: 91697 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1427546 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0336. Min Act: -0.0003

Data Index: 570660 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1557932 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1006712 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1531922 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1315505 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0321. Min Act: -0.0002

Data Index: 133196 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1632841 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0317. Min Act: -0.0002

Data Index: 871562 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0312. Min Act: -0.0002

Data Index: 808911 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1586016 (Python Code)

Max Activating Token Index: 768