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

Dataset: The Pile

Neuron 3487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.6869. Min Act: -0.0000

Data Index: 634075 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.6663. Min Act: -0.0000

Data Index: 1657206 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1579344 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3162. Min Act: -0.0000

Data Index: 966777 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.1466. Min Act: -0.0000

Data Index: 276346 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3706. Min Act: -0.0000

Data Index: 1046445 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.4130. Min Act: -0.0000

Data Index: 500867 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2954. Min Act: -0.0000

Data Index: 816722 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2759. Min Act: -0.0000

Data Index: 373578 (The Pile)

Max Activating Token Index: 554

Text #9

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3243. Min Act: -0.0000

Data Index: 1668205 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3813. Min Act: -0.0000

Data Index: 981534 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1302898 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1828525 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1667834 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1002529 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.1599. Min Act: -0.0000

Data Index: 979335 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2210. Min Act: -0.0000

Data Index: 703634 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2527. Min Act: -0.0000

Data Index: 292178 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2393. Min Act: -0.0000

Data Index: 454280 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 1.6869. Min Range: -1.6869

Max Act: 1.2399. Min Act: -0.0000

Data Index: 993717 (The Pile)

Max Activating Token Index: 979