Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1026 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0005

Data Index: 1104695 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0957. Min Act: -0.0005

Data Index: 663145 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0877. Min Act: -0.0005

Data Index: 1079285 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0874. Min Act: -0.0005

Data Index: 1233936 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0874. Min Act: -0.0005

Data Index: 134244 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0870. Min Act: -0.0005

Data Index: 76325 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0832. Min Act: -0.0005

Data Index: 231692 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0852. Min Act: -0.0005

Data Index: 209761 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0850. Min Act: -0.0005

Data Index: 1346587 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0844. Min Act: -0.0005

Data Index: 858882 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0846. Min Act: -0.0005

Data Index: 897979 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0846. Min Act: -0.0005

Data Index: 220947 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0865. Min Act: -0.0005

Data Index: 1165988 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0800. Min Act: -0.0005

Data Index: 8335 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0820. Min Act: -0.0005

Data Index: 332613 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0817. Min Act: -0.0005

Data Index: 1201598 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0811. Min Act: -0.0005

Data Index: 160216 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0748. Min Act: -0.0005

Data Index: 739270 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0804. Min Act: -0.0005

Data Index: 31240 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0793. Min Act: -0.0005

Data Index: 884518 (C4 (Web Text))

Max Activating Token Index: 253