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

Dataset: The Pile

Neuron 1587 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: 0.8811. Min Range: -0.8811

Max Act: 0.8811. Min Act: -0.0000

Data Index: 405823 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1636642 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1314786 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7057. Min Act: -0.0000

Data Index: 867923 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.7294. Min Act: -0.0000

Data Index: 498837 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5911. Min Act: -0.0000

Data Index: 226617 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1715834 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1317357 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1505091 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5632. Min Act: -0.0000

Data Index: 905194 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5658. Min Act: -0.0000

Data Index: 63570 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1263013 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1942092 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1822651 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1808661 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1584039 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.4718. Min Act: -0.0000

Data Index: 897545 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1302013 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.5083. Min Act: -0.0000

Data Index: 532503 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.8811. Min Range: -0.8811

Max Act: 0.4680. Min Act: -0.0000

Data Index: 625286 (The Pile)

Max Activating Token Index: 277