Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1540243 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1470909 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1523262 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1647858 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1455406 (Python Code)

Max Activating Token Index: 196

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1524827 (Python Code)

Max Activating Token Index: 126

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1423330 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1468438 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1458219 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1406035 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1461315 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1655658 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1486653 (Python Code)

Max Activating Token Index: 475

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1483855 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1569153 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1575460 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1520914 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1420323 (Python Code)

Max Activating Token Index: 902

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1452611 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1562551 (Python Code)

Max Activating Token Index: 64