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

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

Neuron 2479 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: 0.0824. Min Range: -0.0824

Max Act: 0.0819. Min Act: -0.0003

Data Index: 926421 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0003

Data Index: 703423 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1221507 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0802. Min Act: -0.0002

Data Index: 349747 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0776. Min Act: -0.0002

Data Index: 343970 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0777. Min Act: -0.0002

Data Index: 473400 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0773. Min Act: -0.0003

Data Index: 318562 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0743. Min Act: -0.0002

Data Index: 920120 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0765. Min Act: -0.0002

Data Index: 315569 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0764. Min Act: -0.0002

Data Index: 760707 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0769. Min Act: -0.0003

Data Index: 976570 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0699. Min Act: -0.0003

Data Index: 766245 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1033 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1494747 (Python Code)

Max Activating Token Index: 638

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0732. Min Act: -0.0003

Data Index: 318538 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0708. Min Act: -0.0003

Data Index: 174992 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0701. Min Act: -0.0003

Data Index: 375969 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1520107 (Python Code)

Max Activating Token Index: 497

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1611592 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1561669 (Python Code)

Max Activating Token Index: 771