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

Dataset: The Pile

Neuron 4765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1472267 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5904. Min Act: -0.0000

Data Index: 184006 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5301. Min Act: -0.0000

Data Index: 193546 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5491. Min Act: -0.0000

Data Index: 161748 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5331. Min Act: -0.0000

Data Index: 713725 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.5774. Min Act: -0.0000

Data Index: 910784 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1831594 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1833612 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1511575 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1222084 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4476. Min Act: -0.0000

Data Index: 407955 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4584. Min Act: -0.0000

Data Index: 849549 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1660366 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4633. Min Act: -0.0000

Data Index: 573392 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1361406 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4441. Min Act: -0.0000

Data Index: 465443 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4270. Min Act: -0.0000

Data Index: 885977 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1538886 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4649. Min Act: 0.0000

Data Index: 1565703 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.6337. Min Range: -0.6337

Max Act: 0.4359. Min Act: -0.0000

Data Index: 333295 (The Pile)

Max Activating Token Index: 222