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

Dataset: The Pile

Neuron 3346 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: 1.2920. Min Range: -1.2920

Max Act: 1.2920. Min Act: -0.0000

Data Index: 127864 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.2069. Min Act: -0.0000

Data Index: 908994 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1565581 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1557821 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1116. Min Act: -0.0000

Data Index: 90328 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1683697 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1105511 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1037445 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1402090 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0372. Min Act: -0.0000

Data Index: 909459 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1422031 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0680. Min Act: -0.0000

Data Index: 324192 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1520895 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1162336 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1858115 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9283. Min Act: -0.0000

Data Index: 990107 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.8487. Min Act: -0.0000

Data Index: 457808 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1703552 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 1.2920. Min Range: -1.2920

Max Act: 0.9224. Min Act: -0.0000

Data Index: 256782 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.2920. Min Range: -1.2920

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1683351 (The Pile)

Max Activating Token Index: 147