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

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

Neuron 2692 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2878. Min Range: -1.2878

Max Act: 1.2878. Min Act: -0.0001

Data Index: 247974 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.2878. Min Range: -1.2878

Max Act: 1.1184. Min Act: -0.0001

Data Index: 202372 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.2878. Min Range: -1.2878

Max Act: 1.1442. Min Act: -0.0001

Data Index: 153199 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8796. Min Act: -0.0001

Data Index: 1192784 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.9530. Min Act: -0.0001

Data Index: 726196 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8743. Min Act: -0.0001

Data Index: 248500 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.9289. Min Act: -0.0001

Data Index: 1207878 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.9388. Min Act: -0.0001

Data Index: 16216 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8465. Min Act: -0.0001

Data Index: 881041 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8683. Min Act: -0.0001

Data Index: 675801 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8722. Min Act: -0.0001

Data Index: 549577 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8046. Min Act: -0.0001

Data Index: 119189 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7870. Min Act: -0.0001

Data Index: 869804 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8839. Min Act: -0.0001

Data Index: 498614 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1148379 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8546. Min Act: -0.0001

Data Index: 573247 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7730. Min Act: -0.0001

Data Index: 785831 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8170. Min Act: -0.0001

Data Index: 315674 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.8697. Min Act: -0.0001

Data Index: 61785 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.2878. Min Range: -1.2878

Max Act: 0.7923. Min Act: -0.0001

Data Index: 679915 (C4 (Web Text))

Max Activating Token Index: 794