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

Dataset: The Pile

Neuron 4498 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3759. Min Act: -0.0000

Data Index: 902660 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3273. Min Act: -0.0000

Data Index: 847776 (The Pile)

Max Activating Token Index: 203

Text #2

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1273879 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3132. Min Act: -0.0000

Data Index: 512762 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3143. Min Act: -0.0000

Data Index: 681889 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1352757 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1745113 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2896. Min Act: -0.0000

Data Index: 587355 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1308122 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1859299 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2590. Min Act: -0.0000

Data Index: 571722 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2797. Min Act: -0.0000

Data Index: 940211 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1444344 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1153630 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2669. Min Act: -0.0000

Data Index: 334517 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2750. Min Act: -0.0000

Data Index: 189245 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2530. Min Act: -0.0000

Data Index: 279519 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1866431 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1161758 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2684. Min Act: -0.0000

Data Index: 245861 (The Pile)

Max Activating Token Index: 293