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

Dataset: The Pile

Neuron 123 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6376. Min Act: -0.0000

Data Index: 363109 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6723. Min Act: 0.0000

Data Index: 839078 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1435799 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5941. Min Act: -0.0000

Data Index: 715379 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1673447 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5949. Min Act: -0.0000

Data Index: 30630 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5873. Min Act: 0.0000

Data Index: 634994 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5415. Min Act: -0.0000

Data Index: 88259 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5669. Min Act: -0.0000

Data Index: 747324 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5413. Min Act: -0.0000

Data Index: 385110 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1660555 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4984. Min Act: 0.0000

Data Index: 118994 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5168. Min Act: -0.0000

Data Index: 550540 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4836. Min Act: 0.0000

Data Index: 1732157 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1521496 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4677. Min Act: -0.0000

Data Index: 482869 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1087036 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1826076 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1415920 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4900. Min Act: -0.0000

Data Index: 825773 (The Pile)

Max Activating Token Index: 508