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

Dataset: The Pile

Neuron 3478 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5875. Min Range: -3.5875

Max Act: 3.5875. Min Act: -0.0000

Data Index: 909283 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 3.5875. Min Range: -3.5875

Max Act: 3.1848. Min Act: -0.0000

Data Index: 614985 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.4871. Min Act: -0.0000

Data Index: 1354146 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.3106. Min Act: -0.0000

Data Index: 1404198 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.5204. Min Act: -0.0000

Data Index: 1782930 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.2391. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.3486. Min Act: -0.0000

Data Index: 452174 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.1509. Min Act: -0.0000

Data Index: 1995586 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 3.5875. Min Range: -3.5875

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1094336 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9355. Min Act: -0.0000

Data Index: 1995838 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1452110 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9366. Min Act: -0.0000

Data Index: 965372 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9727. Min Act: -0.0000

Data Index: 599387 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9986. Min Act: -0.0000

Data Index: 1994215 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.8515. Min Act: -0.0000

Data Index: 1376787 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9879. Min Act: -0.0000

Data Index: 135180 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9608. Min Act: -0.0000

Data Index: 1686110 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.9975. Min Act: -0.0000

Data Index: 879592 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.7637. Min Act: -0.0000

Data Index: 594896 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 3.5875. Min Range: -3.5875

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1078982 (The Pile)

Max Activating Token Index: 978