Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1996. Min Act: -0.0003

Data Index: 961843 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1975. Min Act: -0.0003

Data Index: 1069014 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1952. Min Act: -0.0003

Data Index: 62098 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1849. Min Act: -0.0003

Data Index: 1152029 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1815. Min Act: -0.0003

Data Index: 43133 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1850. Min Act: -0.0003

Data Index: 1118453 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1678. Min Act: -0.0003

Data Index: 854327 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1670. Min Act: -0.0003

Data Index: 21742 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1637. Min Act: -0.0003

Data Index: 121061 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1668. Min Act: -0.0003

Data Index: 245264 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1733. Min Act: -0.0003

Data Index: 517023 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1675. Min Act: -0.0003

Data Index: 1291975 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1706. Min Act: -0.0003

Data Index: 1057564 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1708. Min Act: -0.0003

Data Index: 293308 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1654. Min Act: -0.0003

Data Index: 876835 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1621. Min Act: -0.0003

Data Index: 882722 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1552. Min Act: -0.0003

Data Index: 520162 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1570. Min Act: -0.0003

Data Index: 241077 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1568. Min Act: -0.0003

Data Index: 465317 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1442. Min Act: -0.0003

Data Index: 914615 (C4 (Web Text))

Max Activating Token Index: 817