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

Dataset: The Pile

Neuron 282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0002. Min Range: -1.0002

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1043367 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1553574 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8930. Min Act: -0.0000

Data Index: 632760 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7807. Min Act: -0.0000

Data Index: 664474 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1033540 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7243. Min Act: -0.0000

Data Index: 419226 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1773089 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6549. Min Act: -0.0000

Data Index: 121245 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6707. Min Act: -0.0000

Data Index: 964013 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6844. Min Act: -0.0000

Data Index: 443143 (The Pile)

Max Activating Token Index: 787

Text #10

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1830230 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1734203 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6606. Min Act: -0.0000

Data Index: 708708 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7054. Min Act: -0.0000

Data Index: 194118 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6138. Min Act: -0.0000

Data Index: 847630 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6474. Min Act: -0.0000

Data Index: 504005 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1252711 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1596205 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6074. Min Act: -0.0000

Data Index: 520337 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1495765 (The Pile)

Max Activating Token Index: 295