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

Dataset: The Pile

Neuron 4693 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: 1.0667. Min Range: -1.0667

Max Act: 1.0667. Min Act: -0.0000

Data Index: 87816 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8564. Min Act: -0.0000

Data Index: 504814 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8941. Min Act: -0.0000

Data Index: 236284 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8629. Min Act: -0.0000

Data Index: 878892 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1915767 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1701951 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1859317 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1235236 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1046298 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1992987 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1570865 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1124561 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6101. Min Act: -0.0000

Data Index: 528376 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6704. Min Act: -0.0000

Data Index: 691966 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1306304 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1246370 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6006. Min Act: -0.0000

Data Index: 720042 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7124. Min Act: -0.0000

Data Index: 142483 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6361. Min Act: -0.0000

Data Index: 123437 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7263. Min Act: -0.0000

Data Index: 435318 (The Pile)

Max Activating Token Index: 1010