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

Dataset: The Pile

Neuron 4064 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: 0.2838. Min Range: -0.2838

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1771885 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2838. Min Act: -0.0000

Data Index: 221013 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2593. Min Act: 0.0000

Data Index: 1456440 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1879. Min Act: 0.0000

Data Index: 658496 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1696996 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1403783 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1835. Min Act: 0.0000

Data Index: 199513 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1732. Min Act: 0.0000

Data Index: 579027 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1198980 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1600091 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1394529 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1764640 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1196921 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1119809 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1696. Min Act: -0.0000

Data Index: 970717 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1658. Min Act: 0.0000

Data Index: 1228745 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1280423 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1599. Min Act: 0.0001

Data Index: 631071 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1699. Min Act: -0.0000

Data Index: 334111 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1631. Min Act: 0.0000

Data Index: 1727121 (The Pile)

Max Activating Token Index: 642