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

Dataset: The Pile

Neuron 1407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.9464. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.9213. Min Act: -0.0000

Data Index: 867324 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1415795 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.8653. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.8741. Min Act: -0.0000

Data Index: 104609 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.9940. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.8446. Min Act: -0.0000

Data Index: 1913161 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.8089. Min Act: -0.0000

Data Index: 1446942 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.7952. Min Act: -0.0000

Data Index: 611566 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.8775. Min Act: -0.0000

Data Index: 1733903 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.7777. Min Act: -0.0000

Data Index: 494218 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.7576. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.6707. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 387

Text #14

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.7016. Min Act: -0.0000

Data Index: 688811 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.6973. Min Act: -0.0000

Data Index: 492848 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1269906 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.5792. Min Act: -0.0000

Data Index: 69371 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.6780. Min Act: -0.0000

Data Index: 967020 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 1.9940. Min Range: -1.9940

Max Act: 1.6698. Min Act: -0.0000

Data Index: 435696 (The Pile)

Max Activating Token Index: 392