Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 38 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1170624 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1016. Min Act: -0.0001

Data Index: 814383 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1101. Min Act: -0.0001

Data Index: 609865 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0927. Min Act: -0.0001

Data Index: 103261 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1239498 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0855. Min Act: -0.0001

Data Index: 505038 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0845. Min Act: -0.0001

Data Index: 971202 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1346911 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1173578 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0958. Min Act: -0.0001

Data Index: 166616 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0857. Min Act: -0.0001

Data Index: 852048 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1146337 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0825. Min Act: -0.0001

Data Index: 10222 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1012891 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0806. Min Act: -0.0001

Data Index: 605884 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0822. Min Act: -0.0001

Data Index: 649314 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0792. Min Act: -0.0001

Data Index: 917740 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0812. Min Act: -0.0001

Data Index: 337448 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0800. Min Act: -0.0001

Data Index: 945961 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0789. Min Act: -0.0001

Data Index: 771896 (C4 (Web Text))

Max Activating Token Index: 346