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

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

Neuron 52 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: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0002

Data Index: 617214 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0729. Min Act: -0.0002

Data Index: 299824 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0744. Min Act: -0.0002

Data Index: 136859 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0698. Min Act: -0.0002

Data Index: 885453 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0735. Min Act: -0.0002

Data Index: 34630 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0707. Min Act: -0.0002

Data Index: 881036 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0711. Min Act: -0.0002

Data Index: 617126 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0700. Min Act: -0.0002

Data Index: 472214 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0695. Min Act: -0.0002

Data Index: 134187 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0674. Min Act: -0.0002

Data Index: 126817 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1055826 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0635. Min Act: -0.0002

Data Index: 462106 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1061428 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1034742 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0646. Min Act: -0.0002

Data Index: 549586 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1228673 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0632. Min Act: -0.0002

Data Index: 577929 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1120975 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0654. Min Act: -0.0002

Data Index: 251646 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1127379 (C4 (Web Text))

Max Activating Token Index: 967