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

Dataset: The Pile

Neuron 726 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: 0.8495. Min Range: -0.8495

Max Act: 0.8275. Min Act: -0.0000

Data Index: 327002 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1619735 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1335982 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1930203 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7208. Min Act: -0.0000

Data Index: 358083 (The Pile)

Max Activating Token Index: 149

Text #5

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1302559 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7057. Min Act: -0.0000

Data Index: 360035 (The Pile)

Max Activating Token Index: 629

Text #7

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6773. Min Act: -0.0000

Data Index: 689280 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6459. Min Act: -0.0000

Data Index: 786255 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1795534 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1106139 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1736723 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6031. Min Act: -0.0000

Data Index: 383712 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1179574 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6273. Min Act: -0.0000

Data Index: 84128 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1609135 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5729. Min Act: -0.0000

Data Index: 851817 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5798. Min Act: -0.0000

Data Index: 750194 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1018519 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1778885 (The Pile)

Max Activating Token Index: 720