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

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

Neuron 1692 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1441053 (Python Code)

Max Activating Token Index: 516

Text #1

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1559456 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1488749 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1389686 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1507376 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1112122 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1615647 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0986. Min Act: -0.0001

Data Index: 622970 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1570574 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1388773 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1543008 (Python Code)

Max Activating Token Index: 904

Text #11

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1389904 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1130707 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1524405 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1556549 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1603836 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1641201 (Python Code)

Max Activating Token Index: 407

Text #17

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1404209 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1495101 (Python Code)

Max Activating Token Index: 198

Text #19

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1540611 (Python Code)

Max Activating Token Index: 539