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

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

Neuron 616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0820. Min Act: -0.0002

Data Index: 6619 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1157722 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0002

Data Index: 174891 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1248954 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1093397 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0715. Min Act: -0.0002

Data Index: 299660 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0747. Min Act: -0.0002

Data Index: 712624 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1062060 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0818. Min Act: -0.0002

Data Index: 682064 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0846. Min Act: -0.0002

Data Index: 136727 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1298665 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0768. Min Act: -0.0002

Data Index: 962683 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1274814 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0762. Min Act: -0.0002

Data Index: 587045 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0753. Min Act: -0.0002

Data Index: 961689 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0774. Min Act: -0.0002

Data Index: 333502 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0668. Min Act: -0.0002

Data Index: 844394 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0695. Min Act: -0.0002

Data Index: 442655 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0668. Min Act: -0.0002

Data Index: 438197 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0718. Min Act: -0.0002

Data Index: 878644 (C4 (Web Text))

Max Activating Token Index: 70