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

Dataset: The Pile

Neuron 3708 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: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1020714 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1267800 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0991. Min Act: -0.0000

Data Index: 715353 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0957. Min Act: -0.0000

Data Index: 441066 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1629294 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0806. Min Act: -0.0000

Data Index: 151600 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0716. Min Act: -0.0000

Data Index: 176512 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0767. Min Act: -0.0000

Data Index: 274725 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1591492 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0744. Min Act: -0.0000

Data Index: 813003 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0763. Min Act: -0.0000

Data Index: 691339 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1009926 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0746. Min Act: -0.0000

Data Index: 408783 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0733. Min Act: -0.0000

Data Index: 832466 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0735. Min Act: -0.0000

Data Index: 574322 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0781. Min Act: -0.0000

Data Index: 27383 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0727. Min Act: -0.0000

Data Index: 762559 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0750. Min Act: -0.0000

Data Index: 928364 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0748. Min Act: -0.0000

Data Index: 265508 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0702. Min Act: -0.0000

Data Index: 261263 (The Pile)

Max Activating Token Index: 351