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

Dataset: The Pile

Neuron 3425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.6133. Min Act: -0.0000

Data Index: 852429 (The Pile)

Max Activating Token Index: 696

Text #1

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1383388 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1979605 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.6041. Min Act: -0.0000

Data Index: 103688 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5638. Min Act: -0.0000

Data Index: 811526 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5775. Min Act: -0.0000

Data Index: 628115 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1814084 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5054. Min Act: -0.0000

Data Index: 838014 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4461. Min Act: -0.0000

Data Index: 554983 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.6021. Min Act: -0.0000

Data Index: 214938 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5273. Min Act: -0.0000

Data Index: 266828 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1147509 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1772720 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1144038 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5084. Min Act: -0.0000

Data Index: 181195 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4823. Min Act: -0.0000

Data Index: 827603 (The Pile)

Max Activating Token Index: 893

Text #16

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4511. Min Act: -0.0000

Data Index: 998842 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1610516 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5232. Min Act: -0.0000

Data Index: 522397 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1189348 (The Pile)

Max Activating Token Index: 159