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

Dataset: The Pile

Neuron 2994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2767. Min Range: -4.2767

Max Act: 4.2767. Min Act: -0.0000

Data Index: 176992 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.5600. Min Act: -0.0000

Data Index: 1304667 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.7107. Min Act: -0.0000

Data Index: 1112342 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.7323. Min Act: -0.0000

Data Index: 1085874 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.5516. Min Act: -0.0000

Data Index: 335715 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.3799. Min Act: -0.0000

Data Index: 1074821 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.2089. Min Act: -0.0000

Data Index: 279513 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.3089. Min Act: -0.0000

Data Index: 534867 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.9231. Min Act: -0.0000

Data Index: 1749609 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.3913. Min Act: -0.0000

Data Index: 1884215 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.1981. Min Act: -0.0000

Data Index: 1457627 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.1884. Min Act: -0.0000

Data Index: 1414646 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.1485. Min Act: -0.0000

Data Index: 1491863 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.1571. Min Act: -0.0000

Data Index: 604437 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.8804. Min Act: -0.0000

Data Index: 1107316 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.0743. Min Act: -0.0000

Data Index: 603045 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.8994. Min Act: -0.0000

Data Index: 634291 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 4.2767. Min Range: -4.2767

Max Act: 3.0663. Min Act: -0.0000

Data Index: 1674673 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.9937. Min Act: -0.0000

Data Index: 1281899 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 4.2767. Min Range: -4.2767

Max Act: 2.8427. Min Act: -0.0000

Data Index: 1042462 (The Pile)

Max Activating Token Index: 346