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

Dataset: The Pile

Neuron 4060 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: 0.9023. Min Range: -0.9023

Max Act: 0.8617. Min Act: -0.0000

Data Index: 962400 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1720055 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1155033 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6955. Min Act: -0.0000

Data Index: 542256 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1235170 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7621. Min Act: -0.0000

Data Index: 636659 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1128728 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7469. Min Act: -0.0000

Data Index: 880774 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1040127 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1549929 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1245504 (The Pile)

Max Activating Token Index: 959

Text #11

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1728265 (The Pile)

Max Activating Token Index: 686

Text #12

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1478716 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7007. Min Act: -0.0000

Data Index: 957647 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7172. Min Act: -0.0000

Data Index: 593216 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6904. Min Act: -0.0000

Data Index: 137109 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6606. Min Act: -0.0000

Data Index: 640038 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1910343 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6543. Min Act: -0.0000

Data Index: 91704 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1769062 (The Pile)

Max Activating Token Index: 818