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

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

Neuron 24 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1465190 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1438169 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1571970 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1634845 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1544019 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0786. Min Act: -0.0000

Data Index: 934252 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1522419 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1514455 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1570595 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1374003 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0755. Min Act: -0.0000

Data Index: 47180 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0755. Min Act: -0.0000

Data Index: 822855 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1458568 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1603722 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1629082 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1531737 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1370821 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1502644 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1429628 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0685. Min Act: -0.0000

Data Index: 762834 (C4 (Web Text))

Max Activating Token Index: 320