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

Dataset: The Pile

Neuron 2019 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: 0.9316. Min Range: -0.9316

Max Act: 0.9316. Min Act: -0.0000

Data Index: 665973 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7034. Min Act: -0.0000

Data Index: 218987 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1084053 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1180842 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1229630 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1537833 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6170. Min Act: -0.0000

Data Index: 635422 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1636301 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5772. Min Act: -0.0000

Data Index: 448271 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1324807 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5962. Min Act: -0.0000

Data Index: 459096 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5813. Min Act: -0.0000

Data Index: 312405 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5640. Min Act: -0.0000

Data Index: 978505 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1690285 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1331404 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5620. Min Act: -0.0000

Data Index: 629951 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5936. Min Act: -0.0000

Data Index: 630460 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5788. Min Act: -0.0000

Data Index: 616496 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1741518 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.5667. Min Act: -0.0000

Data Index: 476250 (The Pile)

Max Activating Token Index: 387