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

Dataset: The Pile

Neuron 4580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2765. Min Act: -0.0000

Data Index: 803798 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1608576 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1895. Min Act: -0.0000

Data Index: 51629 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1949348 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1175379 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1729. Min Act: -0.0000

Data Index: 151991 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1569. Min Act: -0.0000

Data Index: 159707 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1454889 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1560. Min Act: -0.0000

Data Index: 394846 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1500. Min Act: -0.0000

Data Index: 384871 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1508. Min Act: -0.0000

Data Index: 936025 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1325733 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1281317 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1454115 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1769576 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1434. Min Act: -0.0000

Data Index: 850693 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1409. Min Act: -0.0000

Data Index: 153895 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1941179 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1597576 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.2765. Min Range: -0.2765

Max Act: 0.1494. Min Act: -0.0000

Data Index: 612569 (The Pile)

Max Activating Token Index: 875