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

Dataset: The Pile

Neuron 3133 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: 3.1019. Min Range: -3.1019

Max Act: 3.1019. Min Act: -0.0000

Data Index: 1348078 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.6787. Min Act: -0.0000

Data Index: 1295062 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.5355. Min Act: -0.0000

Data Index: 1285853 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.6392. Min Act: -0.0000

Data Index: 1210845 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.6532. Min Act: -0.0000

Data Index: 702653 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.7322. Min Act: -0.0000

Data Index: 308934 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.7277. Min Act: -0.0000

Data Index: 1078596 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.7140. Min Act: -0.0000

Data Index: 1993751 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.5683. Min Act: -0.0000

Data Index: 572373 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.4965. Min Act: -0.0000

Data Index: 672366 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.6007. Min Act: -0.0000

Data Index: 1061221 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.4636. Min Act: -0.0000

Data Index: 1193420 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1418592 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.5460. Min Act: -0.0000

Data Index: 984474 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1635389 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.3914. Min Act: -0.0000

Data Index: 1355158 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.3985. Min Act: -0.0000

Data Index: 1745617 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.2843. Min Act: -0.0000

Data Index: 1087246 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.2811. Min Act: -0.0000

Data Index: 1684281 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 3.1019. Min Range: -3.1019

Max Act: 2.3634. Min Act: -0.0000

Data Index: 377052 (The Pile)

Max Activating Token Index: 1006