Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 53 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1037539 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2235. Min Act: -0.0000

Data Index: 200552 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1072518 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2071. Min Act: -0.0000

Data Index: 882142 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2314. Min Act: -0.0000

Data Index: 905536 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1901. Min Act: -0.0000

Data Index: 534920 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2046. Min Act: -0.0000

Data Index: 549128 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1754. Min Act: -0.0000

Data Index: 215973 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1984. Min Act: -0.0000

Data Index: 247318 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1849. Min Act: -0.0000

Data Index: 942708 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1421017 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1309847 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1661. Min Act: -0.0000

Data Index: 23559 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1785. Min Act: -0.0000

Data Index: 968710 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1845. Min Act: -0.0000

Data Index: 63253 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1719. Min Act: -0.0000

Data Index: 505165 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1646. Min Act: -0.0000

Data Index: 988702 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1744. Min Act: -0.0000

Data Index: 461707 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1638. Min Act: -0.0000

Data Index: 944567 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1307577 (C4 (Web Text))

Max Activating Token Index: 632