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

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

Neuron 505 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2545. Min Act: -0.0000

Data Index: 394905 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2836. Min Act: -0.0000

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2643. Min Act: -0.0000

Data Index: 204311 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1446794 (Python Code)

Max Activating Token Index: 357

Text #4

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2192. Min Act: -0.0000

Data Index: 444185 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1951. Min Act: -0.0000

Data Index: 729783 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1512305 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1937. Min Act: -0.0000

Data Index: 116322 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1629372 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1999. Min Act: -0.0000

Data Index: 807960 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1410072 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1992. Min Act: -0.0000

Data Index: 867109 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1506710 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1597231 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1457412 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1505962 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1481786 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1705. Min Act: -0.0000

Data Index: 999193 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1623295 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1034178 (C4 (Web Text))

Max Activating Token Index: 273