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

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

Neuron 1395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.3440. Min Act: -0.0000

Data Index: 436369 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.3679. Min Act: -0.0000

Data Index: 1013368 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.9429. Min Act: -0.0000

Data Index: 335854 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.0930. Min Act: -0.0000

Data Index: 1307234 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.9112. Min Act: -0.0000

Data Index: 798122 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.8837. Min Act: -0.0000

Data Index: 651892 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.8460. Min Act: -0.0000

Data Index: 260383 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.0278. Min Act: -0.0000

Data Index: 140800 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.9942. Min Act: -0.0000

Data Index: 360109 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.0178. Min Act: -0.0000

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.0089. Min Act: -0.0000

Data Index: 1331256 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.9958. Min Act: -0.0000

Data Index: 652316 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.1609. Min Act: -0.0000

Data Index: 1257921 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.8112. Min Act: -0.0000

Data Index: 416898 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.8652. Min Act: -0.0000

Data Index: 1076855 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 5.3679. Min Range: -5.3679

Max Act: 5.0563. Min Act: -0.0000

Data Index: 43195 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.8630. Min Act: -0.0000

Data Index: 905700 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.6720. Min Act: -0.0000

Data Index: 998319 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.6865. Min Act: -0.0000

Data Index: 105693 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 5.3679. Min Range: -5.3679

Max Act: 4.8629. Min Act: -0.0000

Data Index: 162812 (C4 (Web Text))

Max Activating Token Index: 577