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

Dataset: The Pile

Neuron 1918 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: 0.4332. Min Range: -0.4332

Max Act: 0.4288. Min Act: -0.0000

Data Index: 123128 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3952. Min Act: -0.0000

Data Index: 332605 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1586974 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1949647 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1846700 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1713175 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3551. Min Act: -0.0000

Data Index: 668670 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3852. Min Act: -0.0000

Data Index: 808598 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1670839 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1357252 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1949747 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3226. Min Act: -0.0000

Data Index: 795030 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3227. Min Act: -0.0000

Data Index: 496342 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3013. Min Act: -0.0000

Data Index: 131782 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3057. Min Act: -0.0000

Data Index: 275839 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1930622 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.2986. Min Act: -0.0000

Data Index: 860580 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1016447 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3038. Min Act: -0.0000

Data Index: 733731 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1146840 (The Pile)

Max Activating Token Index: 1004