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

Dataset: The Pile

Neuron 2308 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: 1.5745. Min Range: -1.5745

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1560478 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1680874 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.0895. Min Act: -0.0000

Data Index: 669303 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9871. Min Act: -0.0000

Data Index: 912714 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9705. Min Act: -0.0000

Data Index: 269705 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1361543 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.8730. Min Act: -0.0000

Data Index: 993038 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7703. Min Act: -0.0000

Data Index: 427033 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1879641 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.6846. Min Act: -0.0000

Data Index: 132915 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1305119 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1694988 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1621580 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7720. Min Act: -0.0000

Data Index: 935053 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7899. Min Act: -0.0000

Data Index: 145711 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7142. Min Act: -0.0000

Data Index: 336449 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7220. Min Act: -0.0000

Data Index: 80660 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.6599. Min Act: -0.0000

Data Index: 478037 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1687992 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1318069 (The Pile)

Max Activating Token Index: 74