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

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

Neuron 2471 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1453159 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1393791 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1633317 (Python Code)

Max Activating Token Index: 671

Text #3

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1512170 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1362166 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1534674 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1434842 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1542875 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2695. Min Act: -0.0001

Data Index: 1487029 (Python Code)

Max Activating Token Index: 592

Text #9

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1427336 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1398741 (Python Code)

Max Activating Token Index: 335

Text #11

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2733. Min Act: -0.0001

Data Index: 1548892 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2709. Min Act: -0.0001

Data Index: 1447966 (Python Code)

Max Activating Token Index: 78

Text #13

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2777. Min Act: -0.0001

Data Index: 1515209 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1546646 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2760. Min Act: -0.0001

Data Index: 1416046 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2709. Min Act: -0.0001

Data Index: 1373497 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1470132 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2685. Min Act: -0.0001

Data Index: 1381947 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1589511 (Python Code)

Max Activating Token Index: 50