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

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

Neuron 1584 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: 0.0928. Min Range: -0.0928

Max Act: 0.0916. Min Act: -0.0002

Data Index: 354036 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0002

Data Index: 476342 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1214287 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0829. Min Act: -0.0002

Data Index: 168370 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0844. Min Act: -0.0002

Data Index: 391749 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0795. Min Act: -0.0001

Data Index: 533717 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0810. Min Act: -0.0002

Data Index: 825143 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0791. Min Act: -0.0002

Data Index: 304810 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0760. Min Act: -0.0002

Data Index: 735868 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0827. Min Act: -0.0002

Data Index: 721638 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0767. Min Act: -0.0002

Data Index: 365173 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1122960 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0729. Min Act: -0.0002

Data Index: 73894 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0749. Min Act: -0.0001

Data Index: 114758 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1352009 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1213459 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0748. Min Act: -0.0002

Data Index: 131424 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0736. Min Act: -0.0002

Data Index: 938732 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0762. Min Act: -0.0002

Data Index: 691664 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0759. Min Act: -0.0002

Data Index: 248429 (C4 (Web Text))

Max Activating Token Index: 735