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

Dataset: The Pile

Neuron 618 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: 0.6700. Min Range: -0.6700

Max Act: 0.6700. Min Act: -0.0000

Data Index: 813422 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4327. Min Act: -0.0000

Data Index: 612829 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4476. Min Act: -0.0000

Data Index: 571985 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2924. Min Act: -0.0000

Data Index: 781079 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3630. Min Act: -0.0000

Data Index: 888173 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3511. Min Act: -0.0000

Data Index: 254622 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1858742 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1245338 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3321. Min Act: -0.0000

Data Index: 405420 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2824. Min Act: -0.0000

Data Index: 132148 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1799461 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1785243 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3007. Min Act: -0.0000

Data Index: 302031 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1640773 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2736. Min Act: -0.0000

Data Index: 906348 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2814. Min Act: -0.0000

Data Index: 692039 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2881. Min Act: -0.0000

Data Index: 32083 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2749. Min Act: -0.0000

Data Index: 705657 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2532. Min Act: -0.0000

Data Index: 308919 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.2629. Min Act: -0.0000

Data Index: 422769 (The Pile)

Max Activating Token Index: 949