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

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

Neuron 2379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2779. Min Range: -3.2779

Max Act: 3.2779. Min Act: -0.0000

Data Index: 90970 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 3.2779. Min Range: -3.2779

Max Act: 3.2411. Min Act: -0.0000

Data Index: 405953 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.8428. Min Act: -0.0000

Data Index: 868338 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.8318. Min Act: -0.0000

Data Index: 1037613 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 3.2779. Min Range: -3.2779

Max Act: 3.0538. Min Act: -0.0000

Data Index: 1064556 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.8316. Min Act: -0.0000

Data Index: 198728 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.6781. Min Act: -0.0000

Data Index: 847694 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.6703. Min Act: -0.0000

Data Index: 292686 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1081769 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.5474. Min Act: -0.0001

Data Index: 252592 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.5438. Min Act: -0.0000

Data Index: 480885 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.6383. Min Act: -0.0000

Data Index: 525539 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.6308. Min Act: -0.0000

Data Index: 909283 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.4114. Min Act: -0.0000

Data Index: 805345 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.6580. Min Act: -0.0000

Data Index: 874426 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.4066. Min Act: -0.0000

Data Index: 335991 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.6543. Min Act: -0.0000

Data Index: 395459 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.5068. Min Act: -0.0000

Data Index: 1229689 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1058218 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 3.2779. Min Range: -3.2779

Max Act: 2.5874. Min Act: -0.0000

Data Index: 127465 (C4 (Web Text))

Max Activating Token Index: 531