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

Dataset: The Pile

Neuron 1595 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: 1.5765. Min Range: -1.5765

Max Act: 1.5689. Min Act: -0.0000

Data Index: 62798 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.5765. Min Act: -0.0000

Data Index: 829416 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3940. Min Act: -0.0000

Data Index: 758506 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.4159. Min Act: -0.0000

Data Index: 504318 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3072. Min Act: -0.0000

Data Index: 555446 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3541. Min Act: -0.0000

Data Index: 677037 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3514. Min Act: -0.0000

Data Index: 140152 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.2646. Min Act: -0.0000

Data Index: 1431609 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.4380. Min Act: -0.0000

Data Index: 500427 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1289012 (The Pile)

Max Activating Token Index: 634

Text #10

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3460. Min Act: -0.0000

Data Index: 791422 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3076. Min Act: -0.0000

Data Index: 876070 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1495049 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.1038. Min Act: -0.0000

Data Index: 205009 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.2288. Min Act: -0.0000

Data Index: 530789 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1115074 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.3652. Min Act: -0.0000

Data Index: 760175 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.0758. Min Act: -0.0000

Data Index: 958688 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1145994 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 1.5765. Min Range: -1.5765

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1560390 (The Pile)

Max Activating Token Index: 212