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

Dataset: The Pile

Neuron 3870 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: 0.4715. Min Range: -0.4715

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1601276 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.2308. Min Act: -0.0000

Data Index: 570252 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1882. Min Act: -0.0000

Data Index: 706704 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1722. Min Act: -0.0000

Data Index: 165425 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1776419 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1817. Min Act: -0.0000

Data Index: 542181 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1019614 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1581. Min Act: -0.0000

Data Index: 846425 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1208707 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1580. Min Act: -0.0000

Data Index: 68363 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1487. Min Act: -0.0000

Data Index: 438941 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1468579 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1606. Min Act: -0.0000

Data Index: 254414 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1490. Min Act: -0.0000

Data Index: 215739 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1572. Min Act: -0.0000

Data Index: 140246 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1542. Min Act: -0.0000

Data Index: 425777 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1499042 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1107155 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1421. Min Act: -0.0000

Data Index: 98713 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1514335 (The Pile)

Max Activating Token Index: 768