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

Dataset: The Pile

Neuron 2986 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1300142 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1788889 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6168. Min Act: -0.0000

Data Index: 214272 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6421. Min Act: -0.0000

Data Index: 161498 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1795558 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1814662 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6175. Min Act: -0.0000

Data Index: 371753 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1532171 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5951. Min Act: -0.0000

Data Index: 302878 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.7102. Min Act: -0.0000

Data Index: 464778 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1652302 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5435. Min Act: -0.0000

Data Index: 931570 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1365650 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6071. Min Act: -0.0000

Data Index: 35029 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5031. Min Act: -0.0000

Data Index: 415581 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1598174 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1128593 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5421. Min Act: -0.0000

Data Index: 255550 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5910. Min Act: -0.0000

Data Index: 194706 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1828159 (The Pile)

Max Activating Token Index: 726