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

Dataset: The Pile

Neuron 755 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: 0.1025. Min Range: -0.1025

Max Act: 0.0997. Min Act: -0.0000

Data Index: 48753 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1750098 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1550585 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1771202 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0649. Min Act: -0.0000

Data Index: 818293 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1154010 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1076063 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0497. Min Act: -0.0000

Data Index: 100191 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0427. Min Act: -0.0000

Data Index: 910855 (The Pile)

Max Activating Token Index: 922

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0393. Min Act: -0.0000

Data Index: 324900 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1083779 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0465. Min Act: -0.0000

Data Index: 629660 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0380. Min Act: -0.0000

Data Index: 786997 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0379. Min Act: -0.0000

Data Index: 337015 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0405. Min Act: -0.0000

Data Index: 250625 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0365. Min Act: -0.0000

Data Index: 276119 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0377. Min Act: -0.0000

Data Index: 335344 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1062870 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0344. Min Act: -0.0000

Data Index: 914669 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0314. Min Act: -0.0000

Data Index: 869676 (The Pile)

Max Activating Token Index: 1016