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

Dataset: The Pile

Neuron 5063 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: 1.6884. Min Range: -1.6884

Max Act: 1.6884. Min Act: -0.0000

Data Index: 722787 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.6643. Min Act: -0.0000

Data Index: 201617 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1079974 (The Pile)

Max Activating Token Index: 623

Text #3

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1256859 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1365067 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3863. Min Act: -0.0000

Data Index: 997391 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1036120 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3386. Min Act: -0.0000

Data Index: 594214 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1386660 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2427. Min Act: -0.0000

Data Index: 946933 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3849. Min Act: -0.0000

Data Index: 529310 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3175. Min Act: -0.0000

Data Index: 219684 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1164677 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2704. Min Act: -0.0000

Data Index: 57373 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2207. Min Act: -0.0000

Data Index: 295867 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1279167 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2367. Min Act: -0.0000

Data Index: 197965 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3845. Min Act: -0.0000

Data Index: 211659 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1247113 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2588. Min Act: -0.0000

Data Index: 114756 (The Pile)

Max Activating Token Index: 167