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

Dataset: The Pile

Neuron 5103 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: 0.2673. Min Range: -0.2673

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1519711 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2185. Min Act: -0.0000

Data Index: 608375 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1578253 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1999. Min Act: -0.0000

Data Index: 358804 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1257351 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1743794 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1348715 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1035697 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1974. Min Act: -0.0000

Data Index: 776312 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1300393 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1321519 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2014. Min Act: -0.0000

Data Index: 454647 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1872. Min Act: -0.0000

Data Index: 665001 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1121409 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1954877 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1696844 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1674650 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1596564 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1779. Min Act: -0.0000

Data Index: 98132 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1654977 (The Pile)

Max Activating Token Index: 793