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

Dataset: The Pile

Neuron 2654 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: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1496527 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1315660 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1741503 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1240347 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1982. Min Act: -0.0000

Data Index: 942641 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1934. Min Act: -0.0000

Data Index: 31607 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1738. Min Act: -0.0000

Data Index: 750180 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1831. Min Act: -0.0000

Data Index: 464478 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1731840 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1332514 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1899831 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1801. Min Act: -0.0000

Data Index: 169031 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1644. Min Act: -0.0000

Data Index: 48115 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1599234 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1806288 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1595. Min Act: -0.0000

Data Index: 712640 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1656. Min Act: -0.0000

Data Index: 660616 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1566. Min Act: -0.0000

Data Index: 880549 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1060194 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1622092 (The Pile)

Max Activating Token Index: 695