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

Dataset: The Pile

Neuron 1702 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: 1.6727. Min Range: -1.6727

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1669982 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1942478 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1947714 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1315311 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1733538 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1312910 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1980697 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2959. Min Act: -0.0000

Data Index: 455707 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2517. Min Act: -0.0000

Data Index: 381150 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1079126 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1848023 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1354767 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1525. Min Act: -0.0000

Data Index: 434120 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1027. Min Act: -0.0000

Data Index: 670818 (The Pile)

Max Activating Token Index: 69

Text #14

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1054401 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0700. Min Act: -0.0000

Data Index: 661937 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1276429 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0423. Min Act: -0.0000

Data Index: 609081 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1741380 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 1.6727. Min Range: -1.6727

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1744899 (The Pile)

Max Activating Token Index: 868