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

Dataset: The Pile

Neuron 3952 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: 0.2504. Min Range: -0.2504

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1478345 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1959976 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1245933 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1908886 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1605193 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1783509 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1109310 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1754. Min Act: -0.0000

Data Index: 221660 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1797. Min Act: -0.0000

Data Index: 933326 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1777. Min Act: -0.0000

Data Index: 226226 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1773. Min Act: -0.0000

Data Index: 391056 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1322556 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1196280 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1657. Min Act: -0.0000

Data Index: 908533 (The Pile)

Max Activating Token Index: 860

Text #14

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1872391 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1699. Min Act: -0.0000

Data Index: 378087 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1170427 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1956406 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1605. Min Act: -0.0000

Data Index: 2262 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1551. Min Act: -0.0000

Data Index: 901573 (The Pile)

Max Activating Token Index: 679