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

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

Neuron 1588 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2813. Min Act: -0.0000

Data Index: 959354 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9629. Min Act: 0.0000

Data Index: 290313 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9262. Min Act: -0.0000

Data Index: 634440 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9523. Min Act: 0.0000

Data Index: 1299349 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.9082. Min Act: -0.0000

Data Index: 92484 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.8896. Min Act: -0.0000

Data Index: 516309 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.8056. Min Act: -0.0000

Data Index: 155466 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.8686. Min Act: 0.0000

Data Index: 124342 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.8172. Min Act: -0.0000

Data Index: 465979 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.7781. Min Act: -0.0000

Data Index: 739213 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.7425. Min Act: -0.0000

Data Index: 886293 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.7223. Min Act: -0.0000

Data Index: 759574 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.7087. Min Act: 0.0000

Data Index: 241405 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6815. Min Act: 0.0000

Data Index: 1299847 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6756. Min Act: 0.0000

Data Index: 859660 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1154005 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1019189 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6310. Min Act: -0.0000

Data Index: 903799 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1175169 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.2813. Min Range: -1.2813

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1142899 (C4 (Web Text))

Max Activating Token Index: 170