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

Dataset: The Pile

Neuron 4442 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.4748. Min Act: -0.0000

Data Index: 964863 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3567. Min Act: -0.0000

Data Index: 341628 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1998129 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1457553 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1592. Min Act: -0.0000

Data Index: 1024087 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1570658 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2605. Min Act: -0.0000

Data Index: 637119 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0842. Min Act: -0.0000

Data Index: 11128 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2005. Min Act: -0.0000

Data Index: 608334 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1152. Min Act: -0.0000

Data Index: 779330 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1192. Min Act: -0.0000

Data Index: 335966 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1304. Min Act: -0.0000

Data Index: 176461 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1810. Min Act: -0.0000

Data Index: 28721 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1874665 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1556. Min Act: -0.0000

Data Index: 513268 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1722758 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1129. Min Act: -0.0000

Data Index: 441245 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1701922 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1370. Min Act: -0.0000

Data Index: 973349 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1464915 (The Pile)

Max Activating Token Index: 497