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

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

Neuron 4797 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1040702 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0366. Min Act: -0.0000

Data Index: 441364 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0341. Min Act: -0.0000

Data Index: 946564 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0349. Min Act: -0.0000

Data Index: 923780 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0376. Min Act: -0.0000

Data Index: 545277 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0333. Min Act: -0.0000

Data Index: 860730 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1267938 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0329. Min Act: -0.0000

Data Index: 311865 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0340. Min Act: -0.0000

Data Index: 218767 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0336. Min Act: -0.0000

Data Index: 323754 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1218187 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0336. Min Act: -0.0000

Data Index: 605725 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0308. Min Act: -0.0000

Data Index: 1044079 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1647856 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1275903 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0316. Min Act: -0.0000

Data Index: 527423 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0313. Min Act: -0.0000

Data Index: 711476 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1262998 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0303. Min Act: -0.0000

Data Index: 912355 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0312. Min Act: -0.0000

Data Index: 966145 (C4 (Web Text))

Max Activating Token Index: 69