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

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

Neuron 6067 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: 1.0681. Min Range: -1.0681

Max Act: 1.0681. Min Act: -0.0000

Data Index: 613024 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9277. Min Act: -0.0000

Data Index: 441672 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1329021 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7853. Min Act: -0.0000

Data Index: 54487 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8320. Min Act: -0.0000

Data Index: 684580 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1149146 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1135163 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1062462 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7804. Min Act: -0.0000

Data Index: 156414 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1033043 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7966. Min Act: 0.0000

Data Index: 1059098 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7081. Min Act: 0.0000

Data Index: 565371 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1055356 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8039. Min Act: -0.0000

Data Index: 810921 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7533. Min Act: -0.0000

Data Index: 932756 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7700. Min Act: -0.0000

Data Index: 128800 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7435. Min Act: -0.0000

Data Index: 827643 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7339. Min Act: -0.0000

Data Index: 106685 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7707. Min Act: -0.0000

Data Index: 843213 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1110871 (C4 (Web Text))

Max Activating Token Index: 398