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

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

Neuron 5611 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1651307 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1568965 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1595528 (Python Code)

Max Activating Token Index: 381

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1639007 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1624854 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1421430 (Python Code)

Max Activating Token Index: 398

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1602246 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1583106 (Python Code)

Max Activating Token Index: 848

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1460019 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1376260 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1650869 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1368724 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1618906 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1475679 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1112218 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1560240 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1571752 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1453576 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1432315 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1463611 (Python Code)

Max Activating Token Index: 658