Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2241 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1750336 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1175418 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1609525 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6388. Min Act: -0.0000

Data Index: 612662 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6220. Min Act: -0.0000

Data Index: 175715 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1624406 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6583. Min Act: -0.0000

Data Index: 117024 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5948. Min Act: -0.0000

Data Index: 689683 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1224499 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1256122 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5807. Min Act: -0.0000

Data Index: 758134 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5979. Min Act: -0.0000

Data Index: 267334 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5917. Min Act: -0.0000

Data Index: 557724 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5917. Min Act: -0.0000

Data Index: 958278 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5990. Min Act: -0.0000

Data Index: 29327 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1745862 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1533221 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5637. Min Act: -0.0000

Data Index: 286673 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1284010 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 0.7973. Min Range: -0.7973

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1479441 (The Pile)

Max Activating Token Index: 835