Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1001 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0002

Data Index: 409274 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0819. Min Act: -0.0002

Data Index: 844906 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0747. Min Act: -0.0002

Data Index: 913738 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1263709 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0732. Min Act: -0.0002

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1024912 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0714. Min Act: -0.0002

Data Index: 264123 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0679. Min Act: -0.0002

Data Index: 114774 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0680. Min Act: -0.0002

Data Index: 120107 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1278168 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1117377 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1108743 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0663. Min Act: -0.0002

Data Index: 146231 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1132605 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0678. Min Act: -0.0002

Data Index: 737475 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0658. Min Act: -0.0002

Data Index: 337729 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0658. Min Act: -0.0002

Data Index: 680573 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1290716 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0650. Min Act: -0.0002

Data Index: 465498 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1196221 (C4 (Web Text))

Max Activating Token Index: 949