Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.2051. Min Act: -0.0001

Data Index: 763779 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1911. Min Act: -0.0001

Data Index: 565267 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1208102 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1862. Min Act: -0.0002

Data Index: 25939 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1762. Min Act: -0.0001

Data Index: 627926 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1745. Min Act: -0.0001

Data Index: 608266 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1056781 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1220741 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.2036. Min Act: -0.0002

Data Index: 352026 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1774. Min Act: -0.0001

Data Index: 579727 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1835. Min Act: -0.0002

Data Index: 579539 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1845. Min Act: -0.0001

Data Index: 400649 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1851. Min Act: -0.0001

Data Index: 283568 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1824. Min Act: -0.0001

Data Index: 20584 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1141970 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1344953 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1656. Min Act: -0.0001

Data Index: 295468 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1722. Min Act: -0.0002

Data Index: 414918 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1715. Min Act: -0.0001

Data Index: 567934 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1771. Min Act: -0.0001

Data Index: 625269 (C4 (Web Text))

Max Activating Token Index: 154