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

Dataset: The Pile

Neuron 3262 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0000

Data Index: 598452 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0795. Min Act: -0.0000

Data Index: 729889 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0789. Min Act: -0.0000

Data Index: 392155 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1538529 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1632400 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1680508 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1592467 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1250520 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0621. Min Act: -0.0000

Data Index: 157807 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0621. Min Act: -0.0000

Data Index: 240902 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0589. Min Act: -0.0000

Data Index: 409321 (The Pile)

Max Activating Token Index: 405

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0588. Min Act: -0.0000

Data Index: 635472 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0584. Min Act: -0.0000

Data Index: 104268 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1192130 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1996987 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0543. Min Act: -0.0000

Data Index: 696393 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0536. Min Act: -0.0000

Data Index: 856167 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1503388 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0517. Min Act: -0.0000

Data Index: 29575 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0493. Min Act: -0.0000

Data Index: 705907 (The Pile)

Max Activating Token Index: 124