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

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

Neuron 2573 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.6399. Min Act: 0.0000

Data Index: 1024296 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.6643. Min Act: 0.0001

Data Index: 507674 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.5593. Min Act: 0.0000

Data Index: 1292989 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.5638. Min Act: -0.0000

Data Index: 175459 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3968. Min Act: -0.0000

Data Index: 284340 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4396. Min Act: -0.0000

Data Index: 765016 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4260. Min Act: -0.0000

Data Index: 426991 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3537. Min Act: 0.0001

Data Index: 647088 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4102. Min Act: -0.0000

Data Index: 868635 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4012. Min Act: -0.0000

Data Index: 531654 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3994. Min Act: 0.0001

Data Index: 627117 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3703. Min Act: -0.0000

Data Index: 544347 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2970. Min Act: -0.0000

Data Index: 3556 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3683. Min Act: -0.0000

Data Index: 872879 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3684. Min Act: 0.0001

Data Index: 420355 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3628. Min Act: -0.0000

Data Index: 713121 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3586. Min Act: 0.0001

Data Index: 704374 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1332424 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.4409. Min Act: -0.0000

Data Index: 13720 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.6643. Min Range: -1.6643

Max Act: 1.3271. Min Act: 0.0001

Data Index: 1319643 (C4 (Web Text))

Max Activating Token Index: 60