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

Dataset: The Pile

Neuron 3455 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: 0.6710. Min Range: -0.6710

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1758455 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1700413 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6284. Min Act: 0.0000

Data Index: 1156415 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6703. Min Act: -0.0000

Data Index: 213577 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1186863 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1891602 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6129. Min Act: 0.0000

Data Index: 24905 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1033532 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5431. Min Act: -0.0000

Data Index: 289698 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1901449 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1569974 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5556. Min Act: 0.0000

Data Index: 731309 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5562. Min Act: 0.0000

Data Index: 897641 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1053445 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1024578 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5625. Min Act: -0.0000

Data Index: 437115 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5309. Min Act: 0.0000

Data Index: 1620304 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1656970 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5318. Min Act: 0.0000

Data Index: 1378974 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1202659 (The Pile)

Max Activating Token Index: 584