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

Dataset: The Pile

Neuron 1204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.6844. Min Act: -0.0000

Data Index: 58535 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.5128. Min Act: -0.0000

Data Index: 165084 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.2004. Min Act: -0.0000

Data Index: 911579 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.2787. Min Act: -0.0000

Data Index: 614373 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1732118 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1670495 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1868970 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0300. Min Act: -0.0000

Data Index: 397769 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1417041 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1061514 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1580922 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1649026 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1193. Min Act: -0.0000

Data Index: 948661 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1118641 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.8522. Min Act: -0.0000

Data Index: 404452 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0329. Min Act: -0.0000

Data Index: 965156 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9349. Min Act: -0.0000

Data Index: 222064 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1582613 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9635. Min Act: -0.0000

Data Index: 171872 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1321742 (The Pile)

Max Activating Token Index: 248