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

Dataset: The Pile

Neuron 891 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: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: 0.0000

Data Index: 784152 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0720. Min Act: 0.0000

Data Index: 232307 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1214738 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0713. Min Act: 0.0000

Data Index: 543580 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0711. Min Act: 0.0000

Data Index: 1495342 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0732. Min Act: 0.0000

Data Index: 200692 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1418748 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0704. Min Act: 0.0000

Data Index: 854559 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0702. Min Act: -0.0000

Data Index: 463919 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1354117 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0697. Min Act: -0.0000

Data Index: 224418 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0696. Min Act: 0.0000

Data Index: 1841894 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1722056 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0689. Min Act: -0.0000

Data Index: 403296 (The Pile)

Max Activating Token Index: 2

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0689. Min Act: -0.0000

Data Index: 492433 (The Pile)

Max Activating Token Index: 2

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1871151 (The Pile)

Max Activating Token Index: 2

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1043812 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0685. Min Act: -0.0000

Data Index: 143436 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0684. Min Act: -0.0000

Data Index: 928036 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1164569 (The Pile)

Max Activating Token Index: 1023