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

Dataset: The Pile

Neuron 2753 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: 0.5582. Min Range: -0.5582

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1908168 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1092937 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1472400 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4936. Min Act: -0.0000

Data Index: 906680 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.5028. Min Act: -0.0000

Data Index: 140328 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4785. Min Act: -0.0000

Data Index: 185942 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1814755 (The Pile)

Max Activating Token Index: 701

Text #7

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4521. Min Act: -0.0000

Data Index: 407386 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4690. Min Act: -0.0000

Data Index: 857312 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1298918 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1298963 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1756016 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1002500 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4806. Min Act: -0.0000

Data Index: 878149 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4306. Min Act: -0.0000

Data Index: 336470 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4497. Min Act: -0.0000

Data Index: 275030 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1522461 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3947. Min Act: -0.0000

Data Index: 90232 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1367932 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3953. Min Act: -0.0000

Data Index: 399125 (The Pile)

Max Activating Token Index: 249