Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4878. Min Act: -0.0002

Data Index: 116464 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4000. Min Act: -0.0002

Data Index: 451244 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4265. Min Act: -0.0002

Data Index: 1138822 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4057. Min Act: -0.0002

Data Index: 61743 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3706. Min Act: -0.0001

Data Index: 984826 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3915. Min Act: -0.0002

Data Index: 183178 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4024. Min Act: -0.0002

Data Index: 323029 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3994. Min Act: -0.0002

Data Index: 246029 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.4073. Min Act: -0.0002

Data Index: 592389 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1480528 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3806. Min Act: -0.0001

Data Index: 42845 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3767. Min Act: -0.0002

Data Index: 88197 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3780. Min Act: -0.0002

Data Index: 677962 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3495. Min Act: -0.0002

Data Index: 343983 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3861. Min Act: -0.0001

Data Index: 875156 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3826. Min Act: -0.0002

Data Index: 1230178 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3935. Min Act: -0.0002

Data Index: 900787 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1206596 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3672. Min Act: -0.0002

Data Index: 395065 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.4878. Min Range: -0.4878

Max Act: 0.3644. Min Act: -0.0001

Data Index: 285964 (C4 (Web Text))

Max Activating Token Index: 618