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

Dataset: The Pile

Neuron 326 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: 0.1650. Min Range: -0.1650

Max Act: 0.1650. Min Act: -0.0000

Data Index: 857818 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1601. Min Act: -0.0000

Data Index: 722434 (The Pile)

Max Activating Token Index: 667

Text #2

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1501. Min Act: -0.0000

Data Index: 707850 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1250. Min Act: -0.0000

Data Index: 212224 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1108. Min Act: -0.0000

Data Index: 43558 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1939772 (The Pile)

Max Activating Token Index: 761

Text #6

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1123705 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0993. Min Act: -0.0000

Data Index: 675951 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1484966 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1952902 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1296976 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0962. Min Act: -0.0000

Data Index: 544387 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1734060 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1715354 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1061962 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1297582 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1205435 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1573832 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1977048 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0887. Min Act: -0.0000

Data Index: 657815 (The Pile)

Max Activating Token Index: 745