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

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

Neuron 6052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.1711. Min Act: -0.0001

Data Index: 684583 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.1874. Min Act: -0.0001

Data Index: 378817 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0600. Min Act: -0.0001

Data Index: 1348982 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0899. Min Act: -0.0001

Data Index: 375753 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0023. Min Act: -0.0001

Data Index: 402902 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0500. Min Act: -0.0001

Data Index: 667142 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0058. Min Act: -0.0001

Data Index: 987015 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0094. Min Act: -0.0001

Data Index: 343903 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.9712. Min Act: -0.0001

Data Index: 1050631 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.1874. Min Range: -1.1874

Max Act: 1.0407. Min Act: -0.0001

Data Index: 962875 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.9237. Min Act: -0.0001

Data Index: 734487 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.8781. Min Act: -0.0001

Data Index: 719561 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.9342. Min Act: -0.0001

Data Index: 583652 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.9384. Min Act: -0.0001

Data Index: 170300 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.9429. Min Act: -0.0001

Data Index: 27986 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.8579. Min Act: -0.0001

Data Index: 737348 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.7733. Min Act: -0.0001

Data Index: 881925 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.8555. Min Act: -0.0001

Data Index: 850908 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.8695. Min Act: -0.0001

Data Index: 27927 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.1874. Min Range: -1.1874

Max Act: 0.8692. Min Act: -0.0001

Data Index: 645256 (C4 (Web Text))

Max Activating Token Index: 167