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

Dataset: The Pile

Neuron 635 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.7592. Min Act: -0.0000

Data Index: 48708 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6969. Min Act: -0.0000

Data Index: 1382545 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.6291. Min Act: -0.0000

Data Index: 1463079 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.5105. Min Act: -0.0000

Data Index: 1257135 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.0886. Min Act: -0.0000

Data Index: 1891709 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.0879. Min Act: -0.0000

Data Index: 386526 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.0430. Min Act: -0.0000

Data Index: 66833 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.0757. Min Act: -0.0000

Data Index: 1364033 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.8273. Min Act: -0.0000

Data Index: 256180 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.7535. Min Act: -0.0000

Data Index: 643392 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 3.7592. Min Range: -3.7592

Max Act: 3.0386. Min Act: -0.0000

Data Index: 297410 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.7382. Min Act: -0.0000

Data Index: 1594947 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.8726. Min Act: -0.0000

Data Index: 1815203 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.7751. Min Act: -0.0000

Data Index: 1288085 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.6320. Min Act: -0.0000

Data Index: 955051 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.7525. Min Act: -0.0000

Data Index: 1887841 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.7502. Min Act: -0.0000

Data Index: 1411762 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.6062. Min Act: -0.0000

Data Index: 778169 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.7375. Min Act: -0.0000

Data Index: 1292016 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 3.7592. Min Range: -3.7592

Max Act: 2.6797. Min Act: -0.0000

Data Index: 1411860 (The Pile)

Max Activating Token Index: 467