Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1565 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1815913 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1065002 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1678007 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2358. Min Act: -0.0000

Data Index: 648578 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.2058. Min Act: -0.0000

Data Index: 60053 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1915. Min Act: -0.0000

Data Index: 287093 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1999. Min Act: -0.0000

Data Index: 861653 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1932163 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1922. Min Act: -0.0000

Data Index: 135194 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1869. Min Act: -0.0000

Data Index: 284830 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1791. Min Act: -0.0000

Data Index: 451830 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1711. Min Act: -0.0000

Data Index: 967538 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1754. Min Act: -0.0000

Data Index: 555422 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1810. Min Act: -0.0000

Data Index: 236000 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1871. Min Act: -0.0000

Data Index: 321385 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1780. Min Act: -0.0000

Data Index: 967330 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1917446 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1351831 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1561653 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.2559. Min Range: -0.2559

Max Act: 0.1712. Min Act: -0.0000

Data Index: 991285 (The Pile)

Max Activating Token Index: 517