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

Dataset: The Pile

Neuron 1519 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.9024. Min Act: 0.0001

Data Index: 169055 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.9025. Min Act: -0.0000

Data Index: 962090 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1386166 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1686004 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1796358 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7570. Min Act: 0.0000

Data Index: 371719 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7550. Min Act: 0.0000

Data Index: 960808 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1422715 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1987719 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1791896 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6783. Min Act: 0.0001

Data Index: 1685829 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6794. Min Act: 0.0000

Data Index: 1220354 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1693701 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7186. Min Act: 0.0002

Data Index: 1582984 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1713876 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6928. Min Act: 0.0002

Data Index: 1645007 (The Pile)

Max Activating Token Index: 611

Text #16

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6928. Min Act: -0.0000

Data Index: 791537 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1571320 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1659573 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1722190 (The Pile)

Max Activating Token Index: 98