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

Dataset: The Pile

Neuron 3071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1920010 (The Pile)

Max Activating Token Index: 422

Text #1

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1301795 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4522. Min Act: -0.0000

Data Index: 401840 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1609140 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1207832 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1605214 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4197. Min Act: -0.0000

Data Index: 30047 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1715623 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3694. Min Act: -0.0000

Data Index: 764204 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1593524 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1019828 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3655. Min Act: -0.0000

Data Index: 478503 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1970459 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4045. Min Act: -0.0000

Data Index: 436348 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3953. Min Act: -0.0000

Data Index: 285889 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1365303 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1511384 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1274483 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1265615 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1629510 (The Pile)

Max Activating Token Index: 871