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

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

Neuron 1830 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0878. Min Range: -9.0878

Max Act: 9.0878. Min Act: -0.0001

Data Index: 439865 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 9.0878. Min Range: -9.0878

Max Act: 8.6441. Min Act: -0.0001

Data Index: 20119 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 9.0878. Min Range: -9.0878

Max Act: 8.5765. Min Act: -0.0001

Data Index: 577511 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.9769. Min Act: -0.0001

Data Index: 50592 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.7600. Min Act: -0.0001

Data Index: 1167481 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.7711. Min Act: -0.0001

Data Index: 1323863 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.5012. Min Act: -0.0001

Data Index: 567467 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.9062. Min Act: -0.0001

Data Index: 36079 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.3202. Min Act: -0.0001

Data Index: 624031 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.3920. Min Act: -0.0001

Data Index: 610755 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.1873. Min Act: -0.0001

Data Index: 114359 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.8789. Min Act: -0.0001

Data Index: 141825 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.0675. Min Act: -0.0001

Data Index: 335877 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 9.0878. Min Range: -9.0878

Max Act: 7.1721. Min Act: -0.0001

Data Index: 1262896 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.8378. Min Act: -0.0001

Data Index: 773059 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.8192. Min Act: -0.0001

Data Index: 418908 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.9392. Min Act: -0.0001

Data Index: 1061734 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.7662. Min Act: -0.0001

Data Index: 611888 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.7141. Min Act: -0.0001

Data Index: 1316823 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 9.0878. Min Range: -9.0878

Max Act: 6.7955. Min Act: -0.0001

Data Index: 111371 (C4 (Web Text))

Max Activating Token Index: 444