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

Dataset: The Pile

Neuron 4694 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0000

Data Index: 512110 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1377676 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0636. Min Act: -0.0000

Data Index: 135201 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0615. Min Act: -0.0000

Data Index: 962971 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0593. Min Act: -0.0000

Data Index: 331300 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0613. Min Act: -0.0000

Data Index: 934810 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0612. Min Act: -0.0000

Data Index: 760222 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0610. Min Act: -0.0000

Data Index: 446272 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0609. Min Act: -0.0000

Data Index: 414610 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0606. Min Act: -0.0000

Data Index: 661813 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0604. Min Act: -0.0000

Data Index: 635629 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0602. Min Act: -0.0000

Data Index: 568223 (The Pile)

Max Activating Token Index: 4

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0604. Min Act: -0.0000

Data Index: 481268 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1761022 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0601. Min Act: 0.0000

Data Index: 55618 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1961593 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0599. Min Act: -0.0000

Data Index: 62942 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1408230 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0600. Min Act: 0.0000

Data Index: 1500687 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0600. Min Act: 0.0000

Data Index: 1664688 (The Pile)

Max Activating Token Index: 11