Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2911 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.6111. Min Act: -0.0000

Data Index: 763194 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1565687 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1064985 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5457. Min Act: -0.0000

Data Index: 817590 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1882328 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5375. Min Act: -0.0000

Data Index: 42297 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1631292 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1441034 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1249798 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5081. Min Act: -0.0000

Data Index: 412868 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4916. Min Act: -0.0000

Data Index: 779535 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4858. Min Act: -0.0000

Data Index: 10349 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1648701 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4628. Min Act: -0.0000

Data Index: 314825 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4611. Min Act: -0.0000

Data Index: 234631 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4763. Min Act: -0.0000

Data Index: 843900 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1359299 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4654. Min Act: -0.0000

Data Index: 288924 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4581. Min Act: -0.0000

Data Index: 965789 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1426541 (The Pile)

Max Activating Token Index: 195