Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0317. Min Act: -0.0001

Data Index: 747862 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0322. Min Act: -0.0001

Data Index: 7539 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0301. Min Act: -0.0001

Data Index: 517512 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1335670 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0315. Min Act: -0.0001

Data Index: 460428 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0001

Data Index: 87988 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0308. Min Act: -0.0001

Data Index: 678037 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0297. Min Act: -0.0001

Data Index: 804579 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1072240 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0291. Min Act: -0.0001

Data Index: 471659 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1107534 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1282475 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0305. Min Act: -0.0001

Data Index: 13642 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0284. Min Act: -0.0001

Data Index: 33636 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0277. Min Act: -0.0001

Data Index: 860198 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0273. Min Act: -0.0001

Data Index: 25649 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1064015 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0282. Min Act: -0.0001

Data Index: 910319 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0282. Min Act: -0.0001

Data Index: 417498 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0303. Min Act: -0.0001

Data Index: 407294 (C4 (Web Text))

Max Activating Token Index: 652