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

Dataset: The Pile

Neuron 1736 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: 3.7967. Min Range: -3.7967

Max Act: 3.7967. Min Act: -0.0000

Data Index: 454763 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.3949. Min Act: -0.0000

Data Index: 1474826 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.1059. Min Act: -0.0000

Data Index: 1855035 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.2166. Min Act: -0.0000

Data Index: 1710642 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.4164. Min Act: -0.0000

Data Index: 1165893 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.3179. Min Act: -0.0000

Data Index: 1699133 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.8304. Min Act: -0.0000

Data Index: 570698 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.0305. Min Act: -0.0000

Data Index: 736153 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.8798. Min Act: -0.0000

Data Index: 1949432 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.1733. Min Act: -0.0000

Data Index: 459622 (The Pile)

Max Activating Token Index: 694

Text #10

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9593. Min Act: -0.0000

Data Index: 1223059 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9433. Min Act: -0.0000

Data Index: 1371957 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9090. Min Act: -0.0000

Data Index: 1840925 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9462. Min Act: -0.0000

Data Index: 752564 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9242. Min Act: -0.0000

Data Index: 1992348 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 3.7967. Min Range: -3.7967

Max Act: 3.0640. Min Act: -0.0000

Data Index: 1704615 (The Pile)

Max Activating Token Index: 532

Text #16

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9373. Min Act: -0.0000

Data Index: 1735798 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.6596. Min Act: -0.0000

Data Index: 1740432 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.6276. Min Act: -0.0000

Data Index: 644471 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 3.7967. Min Range: -3.7967

Max Act: 2.9036. Min Act: -0.0000

Data Index: 206937 (The Pile)

Max Activating Token Index: 496