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

Dataset: The Pile

Neuron 4298 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1977715 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1275429 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4780. Min Act: -0.0000

Data Index: 693201 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1739032 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1199245 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3919. Min Act: -0.0000

Data Index: 869507 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1064179 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1151211 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1861433 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1701633 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3717. Min Act: -0.0000

Data Index: 280901 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1792301 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3370. Min Act: -0.0000

Data Index: 425448 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1107280 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1920686 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3857. Min Act: -0.0000

Data Index: 937558 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1619873 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3115. Min Act: -0.0000

Data Index: 681019 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1121643 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1389585 (The Pile)

Max Activating Token Index: 701