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

Dataset: The Pile

Neuron 4083 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: 0.8864. Min Range: -0.8864

Max Act: 0.8864. Min Act: -0.0000

Data Index: 71866 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1185475 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7085. Min Act: -0.0000

Data Index: 582114 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6576. Min Act: -0.0000

Data Index: 397166 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7435. Min Act: -0.0000

Data Index: 154981 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7258. Min Act: -0.0000

Data Index: 741463 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1820544 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1831921 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1090157 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1165514 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1144903 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6757. Min Act: -0.0000

Data Index: 69414 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1650872 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6002. Min Act: -0.0000

Data Index: 474540 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5772. Min Act: -0.0000

Data Index: 960738 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5878. Min Act: -0.0000

Data Index: 637189 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5678. Min Act: -0.0000

Data Index: 53839 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1796976 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1251662 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6000. Min Act: -0.0000

Data Index: 552244 (The Pile)

Max Activating Token Index: 332