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

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

Neuron 128 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1018386 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0898. Min Act: -0.0001

Data Index: 44778 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0827. Min Act: -0.0001

Data Index: 479966 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1021612 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0865. Min Act: -0.0001

Data Index: 689108 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0826. Min Act: -0.0001

Data Index: 465276 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1019067 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0791. Min Act: -0.0001

Data Index: 681 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0749. Min Act: -0.0001

Data Index: 12039 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0760. Min Act: -0.0001

Data Index: 388579 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0762. Min Act: -0.0001

Data Index: 188032 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0704. Min Act: -0.0001

Data Index: 254381 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1098747 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0746. Min Act: -0.0001

Data Index: 161908 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0745. Min Act: -0.0001

Data Index: 392132 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0737. Min Act: -0.0001

Data Index: 949793 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0766. Min Act: -0.0001

Data Index: 336809 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0756. Min Act: -0.0001

Data Index: 969278 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1332166 (C4 (Web Text))

Max Activating Token Index: 485