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

Dataset: The Pile

Neuron 1427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0890. Min Act: -0.0000

Data Index: 17228 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1794228 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9937. Min Act: -0.0000

Data Index: 393643 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1647433 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1709514 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8752. Min Act: -0.0000

Data Index: 872727 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1334467 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9368. Min Act: -0.0000

Data Index: 791301 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9335. Min Act: -0.0000

Data Index: 387623 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0099. Min Act: -0.0000

Data Index: 283469 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1850919 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1324735 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8856. Min Act: -0.0000

Data Index: 992181 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1094636 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1157816 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1468048 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8790. Min Act: -0.0000

Data Index: 129926 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9686. Min Act: -0.0000

Data Index: 489775 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1520018 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8598. Min Act: -0.0000

Data Index: 801548 (The Pile)

Max Activating Token Index: 107