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

Dataset: The Pile

Neuron 3162 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: 1.2495. Min Range: -1.2495

Max Act: 1.1728. Min Act: -0.0000

Data Index: 917802 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.1756. Min Act: -0.0000

Data Index: 847127 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1510182 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.1810. Min Act: -0.0000

Data Index: 239169 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1554571 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1213974 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.1673. Min Act: -0.0000

Data Index: 415512 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1154467 (The Pile)

Max Activating Token Index: 709

Text #8

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.1373. Min Act: -0.0000

Data Index: 669468 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.1498. Min Act: -0.0000

Data Index: 20198 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0514. Min Act: -0.0000

Data Index: 745307 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1599345 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1170257 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 1.2495. Min Range: -1.2495

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1352085 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1454687 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9254. Min Act: -0.0000

Data Index: 512219 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1815149 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1476872 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1929750 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 1.2495. Min Range: -1.2495

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1896577 (The Pile)

Max Activating Token Index: 832