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

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

Neuron 1249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0781. Min Act: -0.0005

Data Index: 1642866 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0717. Min Act: -0.0005

Data Index: 1465565 (Python Code)

Max Activating Token Index: 270

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0770. Min Act: -0.0005

Data Index: 1600357 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0005

Data Index: 1429404 (Python Code)

Max Activating Token Index: 535

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0711. Min Act: -0.0005

Data Index: 1540611 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0705. Min Act: -0.0005

Data Index: 1488246 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1392196 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0701. Min Act: -0.0005

Data Index: 1409454 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0692. Min Act: -0.0005

Data Index: 1590528 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0688. Min Act: -0.0005

Data Index: 1459412 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0671. Min Act: -0.0005

Data Index: 1445309 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0663. Min Act: -0.0005

Data Index: 1537425 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0659. Min Act: -0.0005

Data Index: 1557665 (Python Code)

Max Activating Token Index: 459

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0675. Min Act: -0.0005

Data Index: 1509940 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1506598 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0684. Min Act: -0.0005

Data Index: 1532575 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0712. Min Act: -0.0005

Data Index: 1635654 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0668. Min Act: -0.0005

Data Index: 1525306 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0661. Min Act: -0.0004

Data Index: 1462765 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1393569 (Python Code)

Max Activating Token Index: 63