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

Dataset: The Pile

Neuron 2654 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: 0.8674. Min Range: -0.8674

Max Act: 0.7637. Min Act: -0.0000

Data Index: 20670 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1112015 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1982668 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1449431 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.8299. Min Act: -0.0000

Data Index: 789152 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7309. Min Act: -0.0000

Data Index: 894099 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7122. Min Act: -0.0000

Data Index: 888977 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6948. Min Act: -0.0000

Data Index: 97683 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6720. Min Act: -0.0000

Data Index: 627320 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6908. Min Act: -0.0000

Data Index: 906518 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1736812 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6601. Min Act: -0.0000

Data Index: 655062 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1979018 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6535. Min Act: -0.0000

Data Index: 86991 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1127209 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6159. Min Act: -0.0000

Data Index: 125348 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1951820 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6580. Min Act: -0.0000

Data Index: 47555 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1480594 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 0.8674. Min Range: -0.8674

Max Act: 0.6503. Min Act: -0.0000

Data Index: 737434 (The Pile)

Max Activating Token Index: 416