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

Dataset: The Pile

Neuron 2824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1072578 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1534339 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1589271 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7275. Min Act: -0.0000

Data Index: 3982 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7850. Min Act: -0.0000

Data Index: 490618 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7557. Min Act: -0.0000

Data Index: 749217 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7692. Min Act: -0.0000

Data Index: 702452 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7400. Min Act: -0.0000

Data Index: 585775 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7183. Min Act: -0.0000

Data Index: 811132 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1328811 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7930. Min Act: -0.0000

Data Index: 652697 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7242. Min Act: 0.0000

Data Index: 109593 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6611. Min Act: -0.0000

Data Index: 432051 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6927. Min Act: -0.0000

Data Index: 427002 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1442464 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6642. Min Act: -0.0000

Data Index: 731289 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1988728 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6929. Min Act: -0.0000

Data Index: 574753 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6786. Min Act: -0.0000

Data Index: 51080 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1345263 (The Pile)

Max Activating Token Index: 388