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

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

Neuron 140 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: 2.2102. Min Range: -2.2102

Max Act: 2.2102. Min Act: -0.0000

Data Index: 225745 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 2.2102. Min Range: -2.2102

Max Act: 2.0249. Min Act: -0.0000

Data Index: 1108630 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.9090. Min Act: -0.0000

Data Index: 189631 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 2.2102. Min Range: -2.2102

Max Act: 2.0001. Min Act: -0.0000

Data Index: 804337 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.9222. Min Act: -0.0000

Data Index: 321764 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.8989. Min Act: -0.0000

Data Index: 155463 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.8781. Min Act: -0.0000

Data Index: 885714 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.6805. Min Act: -0.0000

Data Index: 177726 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.7351. Min Act: -0.0000

Data Index: 730908 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.5273. Min Act: -0.0000

Data Index: 215904 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.6126. Min Act: -0.0000

Data Index: 805556 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.5909. Min Act: -0.0000

Data Index: 295431 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.5829. Min Act: -0.0000

Data Index: 815646 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1135367 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.4356. Min Act: -0.0000

Data Index: 366992 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.4926. Min Act: -0.0000

Data Index: 359106 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1262182 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.5686. Min Act: -0.0000

Data Index: 181847 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.4259. Min Act: -0.0000

Data Index: 658176 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 2.2102. Min Range: -2.2102

Max Act: 1.5033. Min Act: -0.0000

Data Index: 953097 (C4 (Web Text))

Max Activating Token Index: 8