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

Dataset: The Pile

Neuron 3090 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3952. Min Act: -0.0000

Data Index: 467047 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1378970 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1966196 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3483. Min Act: -0.0000

Data Index: 422987 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3338. Min Act: -0.0000

Data Index: 714063 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3479. Min Act: -0.0000

Data Index: 931438 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1200835 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3816. Min Act: -0.0000

Data Index: 877280 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3445. Min Act: -0.0000

Data Index: 189638 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3480. Min Act: -0.0000

Data Index: 952356 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3412. Min Act: -0.0000

Data Index: 492413 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3817. Min Act: -0.0000

Data Index: 260141 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3531. Min Act: -0.0000

Data Index: 808450 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1649124 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3576. Min Act: -0.0000

Data Index: 100513 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1456996 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3112. Min Act: -0.0000

Data Index: 714769 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3576. Min Act: -0.0000

Data Index: 171153 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3244. Min Act: -0.0000

Data Index: 776936 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3042. Min Act: -0.0000

Data Index: 304213 (The Pile)

Max Activating Token Index: 1012