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

Dataset: The Pile

Neuron 4029 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: 0.0000

Data Index: 1078974 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0792. Min Act: -0.0000

Data Index: 507716 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0759. Min Act: 0.0000

Data Index: 1057230 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0745. Min Act: 0.0000

Data Index: 1499732 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1102411 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1764014 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0734. Min Act: 0.0000

Data Index: 577019 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0733. Min Act: 0.0000

Data Index: 28600 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1552784 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1169524 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0708. Min Act: -0.0000

Data Index: 871633 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1878609 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0699. Min Act: -0.0000

Data Index: 127541 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0697. Min Act: 0.0000

Data Index: 693607 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0699. Min Act: 0.0000

Data Index: 80705 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0696. Min Act: -0.0000

Data Index: 981673 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1842043 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1587260 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0685. Min Act: 0.0000

Data Index: 1180954 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1673592 (The Pile)

Max Activating Token Index: 1023