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

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

Neuron 536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0888. Min Act: -0.0005

Data Index: 792858 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0832. Min Act: -0.0005

Data Index: 1290553 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0005

Data Index: 610997 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0874. Min Act: -0.0005

Data Index: 604040 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0834. Min Act: -0.0005

Data Index: 59383 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0865. Min Act: -0.0005

Data Index: 297770 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0857. Min Act: -0.0005

Data Index: 19983 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0842. Min Act: -0.0005

Data Index: 799293 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0836. Min Act: -0.0005

Data Index: 783364 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0828. Min Act: -0.0005

Data Index: 365318 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0817. Min Act: -0.0005

Data Index: 211861 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0814. Min Act: -0.0005

Data Index: 1188380 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0779. Min Act: -0.0005

Data Index: 380728 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0815. Min Act: -0.0005

Data Index: 1354127 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0782. Min Act: -0.0005

Data Index: 143786 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0810. Min Act: -0.0005

Data Index: 360915 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0809. Min Act: -0.0005

Data Index: 701617 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0809. Min Act: -0.0005

Data Index: 787788 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0809. Min Act: -0.0005

Data Index: 580794 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0773. Min Act: -0.0005

Data Index: 352343 (C4 (Web Text))

Max Activating Token Index: 298