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

Dataset: The Pile

Neuron 1876 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: 1.6727. Min Range: -1.6727

Max Act: 1.6304. Min Act: -0.0000

Data Index: 1055195 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.6727. Min Act: -0.0000

Data Index: 376847 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2909. Min Act: -0.0000

Data Index: 728798 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1518. Min Act: -0.0000

Data Index: 474038 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1721667 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1940. Min Act: -0.0000

Data Index: 817809 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1926848 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1056966 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2153. Min Act: -0.0000

Data Index: 548928 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1850531 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1089879 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1120. Min Act: -0.0000

Data Index: 461826 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0446. Min Act: -0.0000

Data Index: 664843 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1092. Min Act: -0.0000

Data Index: 852789 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 1.6727. Min Range: -1.6727

Max Act: 0.9781. Min Act: -0.0000

Data Index: 927470 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1820157 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 1.6727. Min Range: -1.6727

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1988039 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1767496 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0607. Min Act: -0.0000

Data Index: 742850 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 1.6727. Min Range: -1.6727

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1822424 (The Pile)

Max Activating Token Index: 301