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

Dataset: The Pile

Neuron 591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1960078 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.7114. Min Act: -0.0000

Data Index: 44542 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1798491 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1150240 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6064. Min Act: -0.0000

Data Index: 848386 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6060. Min Act: -0.0000

Data Index: 379971 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6218. Min Act: -0.0000

Data Index: 486468 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6990. Min Act: -0.0000

Data Index: 244097 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6077. Min Act: -0.0000

Data Index: 896860 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1412763 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5584. Min Act: -0.0000

Data Index: 377763 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1070007 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6244. Min Act: -0.0000

Data Index: 491310 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5945. Min Act: -0.0000

Data Index: 722456 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1564829 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1782832 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1862187 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6216. Min Act: -0.0000

Data Index: 140815 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5935. Min Act: -0.0000

Data Index: 21603 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1732690 (The Pile)

Max Activating Token Index: 850