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

Dataset: The Pile

Neuron 1294 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: 0.9716. Min Range: -0.9716

Max Act: 0.9351. Min Act: -0.0000

Data Index: 936907 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1727049 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1959888 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1050883 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9716. Min Act: -0.0000

Data Index: 627446 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1066678 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1343710 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1468987 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7970. Min Act: -0.0000

Data Index: 37607 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.6561. Min Act: -0.0000

Data Index: 268728 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7808. Min Act: -0.0000

Data Index: 230024 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7252. Min Act: -0.0000

Data Index: 218362 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1423623 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8013. Min Act: -0.0000

Data Index: 978071 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1619888 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1342937 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7024. Min Act: -0.0000

Data Index: 771402 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1109231 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.6572. Min Act: -0.0000

Data Index: 109047 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7055. Min Act: -0.0000

Data Index: 484240 (The Pile)

Max Activating Token Index: 490