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

Dataset: The Pile

Neuron 2730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1942479 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6822. Min Act: -0.0000

Data Index: 77782 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.7228. Min Act: -0.0000

Data Index: 757972 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6835. Min Act: -0.0000

Data Index: 690849 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1038715 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6739. Min Act: 0.0000

Data Index: 1938552 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6379. Min Act: 0.0000

Data Index: 1375894 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6554. Min Act: -0.0000

Data Index: 379458 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6028. Min Act: -0.0000

Data Index: 78317 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6291. Min Act: 0.0001

Data Index: 1060828 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5916. Min Act: -0.0000

Data Index: 793479 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1794023 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6016. Min Act: -0.0000

Data Index: 944185 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1000348 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5621. Min Act: -0.0000

Data Index: 654855 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1249695 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1427323 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5727. Min Act: -0.0000

Data Index: 189614 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5718. Min Act: -0.0000

Data Index: 234581 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1511323 (The Pile)

Max Activating Token Index: 518