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

Dataset: The Pile

Neuron 3674 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1421341 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5511. Min Act: -0.0000

Data Index: 101820 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4953. Min Act: -0.0000

Data Index: 740639 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1445479 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4709. Min Act: -0.0000

Data Index: 130603 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4679. Min Act: -0.0000

Data Index: 905278 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4281. Min Act: -0.0000

Data Index: 37111 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4943. Min Act: -0.0000

Data Index: 657081 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4780. Min Act: -0.0000

Data Index: 728492 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4726. Min Act: -0.0000

Data Index: 534006 (The Pile)

Max Activating Token Index: 544

Text #10

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4699. Min Act: -0.0000

Data Index: 700702 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4435. Min Act: -0.0000

Data Index: 381831 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4422. Min Act: -0.0000

Data Index: 978747 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4537. Min Act: -0.0000

Data Index: 863100 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4233. Min Act: 0.0001

Data Index: 1902670 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4352. Min Act: -0.0000

Data Index: 692691 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1091451 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1698814 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4228. Min Act: -0.0000

Data Index: 465912 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1314542 (The Pile)

Max Activating Token Index: 989