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

Dataset: The Pile

Neuron 3351 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: 0.6018. Min Range: -0.6018

Max Act: 0.6018. Min Act: -0.0000

Data Index: 812178 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.5480. Min Act: -0.0000

Data Index: 898326 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.5422. Min Act: -0.0000

Data Index: 310549 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1522470 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1017781 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1702039 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1115693 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4257. Min Act: -0.0000

Data Index: 866396 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4236. Min Act: -0.0000

Data Index: 255067 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1620567 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4108. Min Act: -0.0000

Data Index: 144574 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4249. Min Act: -0.0000

Data Index: 173593 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4205. Min Act: -0.0000

Data Index: 299596 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.4144. Min Act: -0.0000

Data Index: 542130 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3743. Min Act: -0.0000

Data Index: 650388 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1677253 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1072462 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3769. Min Act: -0.0000

Data Index: 519549 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1069720 (The Pile)

Max Activating Token Index: 942

Text #19

Max Range: 0.6018. Min Range: -0.6018

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1541059 (The Pile)

Max Activating Token Index: 13