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

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

Neuron 3920 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1175047 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.6152. Min Act: 0.0000

Data Index: 1048228 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.6373. Min Act: -0.0000

Data Index: 872091 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5839. Min Act: -0.0000

Data Index: 704629 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5618. Min Act: -0.0000

Data Index: 570809 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5477. Min Act: -0.0000

Data Index: 666286 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5109. Min Act: -0.0000

Data Index: 907374 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4696. Min Act: -0.0000

Data Index: 181064 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1223032 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4745. Min Act: -0.0000

Data Index: 643577 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5111. Min Act: -0.0000

Data Index: 904579 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4683. Min Act: -0.0000

Data Index: 247267 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4631. Min Act: -0.0000

Data Index: 736206 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4571. Min Act: -0.0000

Data Index: 221765 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4605. Min Act: 0.0000

Data Index: 1351893 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4523. Min Act: -0.0000

Data Index: 694952 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4290. Min Act: -0.0000

Data Index: 313473 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1224111 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4332. Min Act: -0.0000

Data Index: 777686 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4209. Min Act: -0.0000

Data Index: 262262 (C4 (Web Text))

Max Activating Token Index: 711