Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5475 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2090. Min Range: -3.2090

Max Act: 3.2090. Min Act: -0.0000

Data Index: 220089 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 3.2090. Min Range: -3.2090

Max Act: 2.9836. Min Act: -0.0000

Data Index: 236970 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.2090. Min Range: -3.2090

Max Act: 2.2846. Min Act: -0.0000

Data Index: 243533 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 3.2090. Min Range: -3.2090

Max Act: 2.3864. Min Act: -0.0000

Data Index: 433089 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 3.2090. Min Range: -3.2090

Max Act: 2.0468. Min Act: -0.0000

Data Index: 839699 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.9911. Min Act: -0.0000

Data Index: 650198 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.9068. Min Act: -0.0000

Data Index: 949409 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.2090. Min Range: -3.2090

Max Act: 2.0026. Min Act: -0.0000

Data Index: 468591 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.8811. Min Act: -0.0000

Data Index: 974947 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.9604. Min Act: -0.0000

Data Index: 727468 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.9314. Min Act: -0.0000

Data Index: 920638 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.9049. Min Act: -0.0000

Data Index: 611773 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.8372. Min Act: -0.0000

Data Index: 380143 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.8300. Min Act: -0.0000

Data Index: 1347829 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.7989. Min Act: -0.0000

Data Index: 249977 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.7921. Min Act: -0.0000

Data Index: 505631 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.9119. Min Act: -0.0000

Data Index: 121076 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.8515. Min Act: -0.0000

Data Index: 850725 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.6784. Min Act: -0.0000

Data Index: 656435 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.2090. Min Range: -3.2090

Max Act: 1.7709. Min Act: -0.0000

Data Index: 28748 (C4 (Web Text))

Max Activating Token Index: 709