Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 746 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0978. Min Act: -0.0004

Data Index: 1019317 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0987. Min Act: -0.0004

Data Index: 864092 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0947. Min Act: -0.0004

Data Index: 339895 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0964. Min Act: -0.0004

Data Index: 638257 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0929. Min Act: -0.0004

Data Index: 681502 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0004

Data Index: 507208 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0900. Min Act: -0.0004

Data Index: 745902 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0952. Min Act: -0.0004

Data Index: 565104 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0958. Min Act: -0.0004

Data Index: 579106 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0973. Min Act: -0.0004

Data Index: 1209066 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0861. Min Act: -0.0004

Data Index: 191165 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0947. Min Act: -0.0004

Data Index: 1810851 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0890. Min Act: -0.0004

Data Index: 678936 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0918. Min Act: -0.0004

Data Index: 275789 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0846. Min Act: -0.0004

Data Index: 1639788 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0888. Min Act: -0.0004

Data Index: 1105573 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0887. Min Act: -0.0004

Data Index: 724790 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0892. Min Act: -0.0004

Data Index: 755211 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0876. Min Act: -0.0004

Data Index: 1472055 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0889. Min Act: -0.0004

Data Index: 1809999 (The Pile)

Max Activating Token Index: 334