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

Dataset: The Pile

Neuron 3228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1005116 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4306. Min Act: -0.0000

Data Index: 460234 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1256803 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4007. Min Act: -0.0000

Data Index: 224695 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1322546 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1790848 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3939. Min Act: -0.0000

Data Index: 690412 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1649884 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1848170 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1406663 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3832. Min Act: -0.0000

Data Index: 508617 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1970338 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1203596 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1095593 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1769185 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3560. Min Act: -0.0000

Data Index: 599557 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1932471 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3563. Min Act: -0.0000

Data Index: 937557 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3543. Min Act: -0.0000

Data Index: 651037 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3662. Min Act: -0.0000

Data Index: 926132 (The Pile)

Max Activating Token Index: 229