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

Dataset: The Pile

Neuron 380 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: 0.5754. Min Range: -0.5754

Max Act: 0.5754. Min Act: -0.0000

Data Index: 299194 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1351825 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5513. Min Act: -0.0000

Data Index: 593973 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5625. Min Act: -0.0000

Data Index: 791794 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1916554 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1730755 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5225. Min Act: -0.0000

Data Index: 751797 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1114345 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5124. Min Act: -0.0000

Data Index: 291501 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1518379 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1372382 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1529865 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1536605 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1473629 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5056. Min Act: -0.0001

Data Index: 45193 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5005. Min Act: -0.0000

Data Index: 865733 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1859841 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1266704 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1890619 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1377870 (The Pile)

Max Activating Token Index: 841