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

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

Neuron 622 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0003

Data Index: 409504 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1277461 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1245874 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0760. Min Act: -0.0002

Data Index: 531677 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0756. Min Act: -0.0002

Data Index: 792284 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0756. Min Act: -0.0002

Data Index: 744225 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0782. Min Act: -0.0002

Data Index: 687701 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1125642 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1278796 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0776. Min Act: -0.0003

Data Index: 143881 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1274357 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1085516 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0736. Min Act: -0.0003

Data Index: 734950 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0708. Min Act: -0.0003

Data Index: 856140 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0715. Min Act: -0.0003

Data Index: 410361 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0742. Min Act: -0.0003

Data Index: 514136 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1013101 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0721. Min Act: -0.0003

Data Index: 833123 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1253963 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0731. Min Act: -0.0003

Data Index: 473489 (C4 (Web Text))

Max Activating Token Index: 265