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

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

Neuron 375 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: 6.6829. Min Range: -6.6829

Max Act: 6.6829. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 6.6829. Min Range: -6.6829

Max Act: 4.8538. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 6.6829. Min Range: -6.6829

Max Act: 4.7415. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 6.6829. Min Range: -6.6829

Max Act: 4.1226. Min Act: -0.0000

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.9087. Min Act: -0.0000

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 6.6829. Min Range: -6.6829

Max Act: 4.2908. Min Act: -0.0000

Data Index: 1291574 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.7962. Min Act: -0.0000

Data Index: 1131400 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.0603. Min Act: -0.0000

Data Index: 460060 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.4735. Min Act: -0.0000

Data Index: 1307956 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.2620. Min Act: -0.0000

Data Index: 1049642 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.3270. Min Act: -0.0000

Data Index: 520349 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.4527. Min Act: -0.0000

Data Index: 121203 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.1340. Min Act: -0.0000

Data Index: 932668 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.0766. Min Act: -0.0000

Data Index: 931070 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 6.6829. Min Range: -6.6829

Max Act: 2.9110. Min Act: -0.0000

Data Index: 219844 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.0849. Min Act: -0.0000

Data Index: 676754 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.2213. Min Act: -0.0000

Data Index: 649946 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.0763. Min Act: -0.0000

Data Index: 867808 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.0551. Min Act: -0.0000

Data Index: 579666 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 6.6829. Min Range: -6.6829

Max Act: 3.0501. Min Act: -0.0000

Data Index: 173496 (C4 (Web Text))

Max Activating Token Index: 18