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

Dataset: The Pile

Neuron 2162 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.8069. Min Act: -0.0000

Data Index: 1957705 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4447. Min Act: -0.0000

Data Index: 1349148 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.3766. Min Act: -0.0000

Data Index: 316904 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4931. Min Act: -0.0000

Data Index: 1108437 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1733. Min Act: -0.0000

Data Index: 743174 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.2928. Min Act: -0.0000

Data Index: 264384 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.2337. Min Act: -0.0000

Data Index: 508457 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1152508 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.8069. Min Range: -1.8069

Max Act: 0.9948. Min Act: -0.0000

Data Index: 98529 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.8069. Min Range: -1.8069

Max Act: 0.9929. Min Act: -0.0000

Data Index: 651853 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 1.8069. Min Range: -1.8069

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1598630 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0237. Min Act: -0.0000

Data Index: 621309 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0570. Min Act: -0.0000

Data Index: 146981 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0756. Min Act: -0.0000

Data Index: 477979 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1938522 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0478. Min Act: -0.0000

Data Index: 897519 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.8069. Min Range: -1.8069

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1783657 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 1.8069. Min Range: -1.8069

Max Act: 0.9086. Min Act: -0.0000

Data Index: 36209 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.0467. Min Act: -0.0000

Data Index: 131097 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 1.8069. Min Range: -1.8069

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1645936 (The Pile)

Max Activating Token Index: 156