Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3239 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1405737 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1247723 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0366. Min Act: -0.0000

Data Index: 745653 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0328. Min Act: -0.0000

Data Index: 33057 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0320. Min Act: -0.0000

Data Index: 386823 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0307. Min Act: -0.0000

Data Index: 772363 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1319382 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0308. Min Act: -0.0001

Data Index: 160344 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0294. Min Act: -0.0001

Data Index: 382099 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0291. Min Act: -0.0000

Data Index: 179641 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0288. Min Act: -0.0000

Data Index: 782771 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1314456 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1036867 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0281. Min Act: -0.0001

Data Index: 84916 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0276. Min Act: -0.0000

Data Index: 406319 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0272. Min Act: -0.0000

Data Index: 545626 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0263. Min Act: -0.0000

Data Index: 249615 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0274. Min Act: -0.0000

Data Index: 194184 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0291. Min Act: -0.0000

Data Index: 847374 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0274. Min Act: -0.0000

Data Index: 1299480 (C4 (Web Text))

Max Activating Token Index: 152