Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3052 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.1017. Min Act: -0.0003

Data Index: 168599 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0970. Min Act: -0.0003

Data Index: 643036 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0936. Min Act: -0.0003

Data Index: 639951 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0936. Min Act: -0.0003

Data Index: 765001 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0885. Min Act: -0.0003

Data Index: 42023 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0882. Min Act: -0.0003

Data Index: 654931 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0887. Min Act: -0.0003

Data Index: 12057 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0856. Min Act: -0.0003

Data Index: 1278748 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0890. Min Act: -0.0003

Data Index: 84343 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1078265 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0811. Min Act: -0.0003

Data Index: 491755 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1591793 (Python Code)

Max Activating Token Index: 654

Text #12

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0795. Min Act: -0.0003

Data Index: 353467 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0796. Min Act: -0.0003

Data Index: 595047 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0796. Min Act: -0.0003

Data Index: 605221 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0796. Min Act: -0.0003

Data Index: 681139 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1016305 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0758. Min Act: -0.0003

Data Index: 530200 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0782. Min Act: -0.0003

Data Index: 140813 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1457867 (Python Code)

Max Activating Token Index: 20