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

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

Neuron 3253 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: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0001

Data Index: 727131 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1254990 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0864. Min Act: -0.0001

Data Index: 967121 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0871. Min Act: -0.0001

Data Index: 721728 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0832. Min Act: -0.0001

Data Index: 370022 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0850. Min Act: -0.0001

Data Index: 105484 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1142681 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1262359 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0848. Min Act: -0.0001

Data Index: 746427 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1448666 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0867. Min Act: -0.0001

Data Index: 591499 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1117690 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0801. Min Act: -0.0001

Data Index: 906378 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0893. Min Act: -0.0001

Data Index: 987398 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1197389 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0811. Min Act: -0.0001

Data Index: 888009 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0836. Min Act: -0.0001

Data Index: 580523 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1008956 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0799. Min Act: -0.0001

Data Index: 290134 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0754. Min Act: -0.0001

Data Index: 816655 (C4 (Web Text))

Max Activating Token Index: 179