Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2052 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1045547 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1601491 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4340. Min Act: -0.0000

Data Index: 86332 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4011. Min Act: -0.0000

Data Index: 109117 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3908. Min Act: -0.0000

Data Index: 61774 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4119. Min Act: -0.0000

Data Index: 946429 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1733720 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1390693 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3855. Min Act: -0.0000

Data Index: 814577 (The Pile)

Max Activating Token Index: 742

Text #9

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1189583 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3454. Min Act: -0.0000

Data Index: 717763 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3680. Min Act: -0.0000

Data Index: 154406 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3528. Min Act: -0.0000

Data Index: 637861 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1541240 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3641. Min Act: -0.0000

Data Index: 902463 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1432354 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3724. Min Act: -0.0000

Data Index: 69455 (The Pile)

Max Activating Token Index: 915

Text #17

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3328. Min Act: -0.0001

Data Index: 600999 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1279539 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1094850 (The Pile)

Max Activating Token Index: 1008