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

Dataset: The Pile

Neuron 3729 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: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: 0.0000

Data Index: 8110 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0731. Min Act: 0.0000

Data Index: 1708114 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0729. Min Act: 0.0000

Data Index: 1889964 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0694. Min Act: 0.0000

Data Index: 352415 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0704. Min Act: 0.0000

Data Index: 1225937 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0694. Min Act: 0.0000

Data Index: 1563197 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1279903 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0689. Min Act: 0.0000

Data Index: 445702 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0689. Min Act: 0.0000

Data Index: 786879 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0686. Min Act: 0.0000

Data Index: 1115442 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0662. Min Act: -0.0000

Data Index: 780548 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0684. Min Act: 0.0000

Data Index: 1849011 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0680. Min Act: 0.0000

Data Index: 1533564 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0654. Min Act: 0.0000

Data Index: 1429336 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0676. Min Act: 0.0000

Data Index: 422816 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0676. Min Act: -0.0000

Data Index: 459880 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0675. Min Act: 0.0000

Data Index: 1085205 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0672. Min Act: -0.0000

Data Index: 308927 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0647. Min Act: 0.0000

Data Index: 1175871 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0669. Min Act: 0.0000

Data Index: 1829297 (The Pile)

Max Activating Token Index: 1023