Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5839 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1059907 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1247316 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.8226. Min Act: -0.0000

Data Index: 828644 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6491. Min Act: -0.0000

Data Index: 280 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1002952 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6528. Min Act: -0.0000

Data Index: 499034 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1026336 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1323150 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6430. Min Act: -0.0000

Data Index: 148356 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5692. Min Act: -0.0000

Data Index: 314174 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5355. Min Act: -0.0000

Data Index: 487465 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6242. Min Act: -0.0000

Data Index: 466870 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5763. Min Act: -0.0000

Data Index: 280409 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5969. Min Act: -0.0000

Data Index: 926114 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1358581 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5375. Min Act: -0.0000

Data Index: 936531 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5032. Min Act: -0.0000

Data Index: 832307 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1000062 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1338575 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5151. Min Act: -0.0000

Data Index: 554077 (C4 (Web Text))

Max Activating Token Index: 144