Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1548 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0895. Min Act: -0.0006

Data Index: 997737 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0960. Min Act: -0.0006

Data Index: 276357 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0824. Min Act: -0.0006

Data Index: 258199 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0816. Min Act: -0.0006

Data Index: 1199808 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0801. Min Act: -0.0006

Data Index: 1211045 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0786. Min Act: -0.0006

Data Index: 762229 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0751. Min Act: -0.0006

Data Index: 16006 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0810. Min Act: -0.0006

Data Index: 925057 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0772. Min Act: -0.0006

Data Index: 814274 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0794. Min Act: -0.0006

Data Index: 193467 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0745. Min Act: -0.0006

Data Index: 156130 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0710. Min Act: -0.0006

Data Index: 505973 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0779. Min Act: -0.0006

Data Index: 885522 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0726. Min Act: -0.0006

Data Index: 1048754 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0734. Min Act: -0.0006

Data Index: 413667 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0671. Min Act: -0.0006

Data Index: 772435 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0720. Min Act: -0.0006

Data Index: 1138307 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0711. Min Act: -0.0006

Data Index: 841928 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0738. Min Act: -0.0006

Data Index: 617025 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0709. Min Act: -0.0006

Data Index: 1294953 (C4 (Web Text))

Max Activating Token Index: 151