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

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

Neuron 1318 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.2502. Min Act: -0.0001

Data Index: 1077244 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.3357. Min Act: -0.0001

Data Index: 226669 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.1633. Min Act: -0.0001

Data Index: 382168 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0745. Min Act: -0.0001

Data Index: 1295853 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.1458. Min Act: -0.0001

Data Index: 248805 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0417. Min Act: -0.0001

Data Index: 269186 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.1685. Min Act: -0.0001

Data Index: 479498 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0508. Min Act: -0.0001

Data Index: 484602 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0781. Min Act: -0.0001

Data Index: 586229 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0418. Min Act: -0.0001

Data Index: 51311 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0304. Min Act: -0.0000

Data Index: 52846 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.3357. Min Range: -1.3357

Max Act: 0.9479. Min Act: -0.0001

Data Index: 122639 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.3357. Min Range: -1.3357

Max Act: 0.9353. Min Act: -0.0001

Data Index: 160368 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.3357. Min Range: -1.3357

Max Act: 0.9402. Min Act: -0.0001

Data Index: 739171 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.3357. Min Range: -1.3357

Max Act: 0.9236. Min Act: -0.0001

Data Index: 162900 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.3357. Min Range: -1.3357

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1230751 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.3357. Min Range: -1.3357

Max Act: 0.9684. Min Act: -0.0001

Data Index: 213635 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0065. Min Act: -0.0001

Data Index: 1223728 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0274. Min Act: -0.0001

Data Index: 3475 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.3357. Min Range: -1.3357

Max Act: 1.0027. Min Act: -0.0001

Data Index: 1154519 (C4 (Web Text))

Max Activating Token Index: 292