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

Dataset: The Pile

Neuron 2144 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: 0.5800. Min Range: -0.5800

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1539286 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5800. Min Act: -0.0000

Data Index: 716397 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4635. Min Act: -0.0000

Data Index: 701580 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1346993 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5084. Min Act: -0.0000

Data Index: 853103 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4891. Min Act: -0.0000

Data Index: 409272 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5114. Min Act: -0.0000

Data Index: 870649 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4820. Min Act: -0.0000

Data Index: 368069 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1588601 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4555. Min Act: -0.0000

Data Index: 133147 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1813599 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3963. Min Act: -0.0000

Data Index: 638054 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4160. Min Act: -0.0000

Data Index: 255698 (The Pile)

Max Activating Token Index: 652

Text #13

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1563130 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4213. Min Act: -0.0000

Data Index: 552032 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1647457 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1608837 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1907060 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4015. Min Act: -0.0000

Data Index: 256286 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1653749 (The Pile)

Max Activating Token Index: 111