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

Dataset: The Pile

Neuron 1045 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0798. Min Act: -0.0000

Data Index: 515893 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1273314 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1988561 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0746. Min Act: -0.0000

Data Index: 693418 (The Pile)

Max Activating Token Index: 362

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1948283 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0669. Min Act: -0.0000

Data Index: 433272 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1445199 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0741. Min Act: -0.0000

Data Index: 514255 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1390022 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1245586 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0657. Min Act: -0.0000

Data Index: 786275 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1155762 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0604. Min Act: -0.0000

Data Index: 924543 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0698. Min Act: -0.0000

Data Index: 761073 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0573. Min Act: -0.0000

Data Index: 899990 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1041511 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0609. Min Act: -0.0000

Data Index: 138391 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0621. Min Act: 0.0000

Data Index: 1384332 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1671626 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0637. Min Act: -0.0000

Data Index: 507286 (The Pile)

Max Activating Token Index: 186