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

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

Neuron 4585 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1053. Min Act: -0.0001

Data Index: 575800 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0001

Data Index: 814122 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1000. Min Act: -0.0001

Data Index: 371073 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0968. Min Act: -0.0001

Data Index: 8667 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1309367 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0872. Min Act: -0.0001

Data Index: 64308 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1064454 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0845. Min Act: -0.0001

Data Index: 333833 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0828. Min Act: -0.0001

Data Index: 213215 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0775. Min Act: -0.0001

Data Index: 403380 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0800. Min Act: -0.0001

Data Index: 247795 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0798. Min Act: -0.0001

Data Index: 117044 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0797. Min Act: -0.0001

Data Index: 905059 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0791. Min Act: -0.0001

Data Index: 638491 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1241461 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0755. Min Act: -0.0001

Data Index: 869631 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0780. Min Act: -0.0001

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0747. Min Act: -0.0001

Data Index: 79265 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0774. Min Act: -0.0001

Data Index: 900367 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0749. Min Act: -0.0001

Data Index: 570829 (C4 (Web Text))

Max Activating Token Index: 694