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

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

Neuron 4451 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.4046. Min Act: -0.0001

Data Index: 602576 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0666. Min Act: -0.0001

Data Index: 514686 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0936. Min Act: -0.0001

Data Index: 1200834 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0689. Min Act: -0.0001

Data Index: 1261221 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0710. Min Act: -0.0001

Data Index: 479089 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.4046. Min Range: -1.4046

Max Act: 0.9753. Min Act: -0.0001

Data Index: 357147 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0444. Min Act: -0.0001

Data Index: 676820 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0952. Min Act: -0.0001

Data Index: 377891 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0363. Min Act: -0.0001

Data Index: 716839 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0654. Min Act: -0.0001

Data Index: 831000 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0170. Min Act: -0.0001

Data Index: 337313 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0601. Min Act: -0.0001

Data Index: 1041463 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0174. Min Act: -0.0001

Data Index: 484761 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0209. Min Act: -0.0001

Data Index: 426030 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0539. Min Act: -0.0001

Data Index: 961432 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0373. Min Act: -0.0001

Data Index: 347335 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 1.4046. Min Range: -1.4046

Max Act: 0.9828. Min Act: -0.0001

Data Index: 516795 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0349. Min Act: -0.0001

Data Index: 203947 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.4046. Min Range: -1.4046

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1062961 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 1.4046. Min Range: -1.4046

Max Act: 0.9697. Min Act: -0.0001

Data Index: 988625 (C4 (Web Text))

Max Activating Token Index: 499