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

Dataset: The Pile

Neuron 4183 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0531. Min Range: -3.0531

Max Act: 3.0531. Min Act: -0.0000

Data Index: 735898 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.6057. Min Act: -0.0000

Data Index: 529511 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.4483. Min Act: -0.0000

Data Index: 174206 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.4306. Min Act: -0.0000

Data Index: 611923 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.5525. Min Act: -0.0000

Data Index: 1562203 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.2893. Min Act: -0.0000

Data Index: 1883865 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.0311. Min Act: -0.0000

Data Index: 306552 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.2694. Min Act: -0.0000

Data Index: 830892 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.1021. Min Act: -0.0000

Data Index: 1491723 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.1442. Min Act: -0.0000

Data Index: 552138 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.0134. Min Act: -0.0000

Data Index: 826756 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 3.0531. Min Range: -3.0531

Max Act: 1.9923. Min Act: -0.0000

Data Index: 503830 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 3.0531. Min Range: -3.0531

Max Act: 1.9583. Min Act: -0.0000

Data Index: 317179 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 3.0531. Min Range: -3.0531

Max Act: 1.8202. Min Act: -0.0000

Data Index: 720754 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 3.0531. Min Range: -3.0531

Max Act: 1.9566. Min Act: -0.0000

Data Index: 588221 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.0362. Min Act: -0.0000

Data Index: 324207 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.0230. Min Act: -0.0000

Data Index: 1162564 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.0045. Min Act: -0.0000

Data Index: 995610 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 3.0531. Min Range: -3.0531

Max Act: 1.8779. Min Act: -0.0000

Data Index: 1911768 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 3.0531. Min Range: -3.0531

Max Act: 1.8873. Min Act: -0.0000

Data Index: 74456 (The Pile)

Max Activating Token Index: 729