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

Dataset: The Pile

Neuron 3484 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: 0.3032. Min Range: -0.3032

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1946955 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1919762 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2824. Min Act: -0.0000

Data Index: 747733 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2999. Min Act: -0.0000

Data Index: 270252 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1009152 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1743155 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2848. Min Act: -0.0000

Data Index: 293186 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1805882 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.3014. Min Act: -0.0000

Data Index: 204235 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2903. Min Act: -0.0000

Data Index: 756559 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2899. Min Act: -0.0000

Data Index: 394940 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1018182 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2756. Min Act: -0.0000

Data Index: 77173 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1476370 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2845. Min Act: -0.0000

Data Index: 583766 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2813. Min Act: -0.0000

Data Index: 718812 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1943471 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1738660 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1232300 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.3032. Min Range: -0.3032

Max Act: 0.2816. Min Act: -0.0000

Data Index: 555378 (The Pile)

Max Activating Token Index: 74