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

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

Neuron 3736 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0001

Data Index: 838426 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1007. Min Act: -0.0001

Data Index: 730766 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1035. Min Act: -0.0001

Data Index: 64528 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1153470 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1245767 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1251077 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0904. Min Act: -0.0001

Data Index: 826953 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1274548 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0860. Min Act: -0.0001

Data Index: 872089 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1349821 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0929. Min Act: -0.0001

Data Index: 919722 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0868. Min Act: -0.0001

Data Index: 527502 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1191985 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0923. Min Act: -0.0001

Data Index: 228451 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0854. Min Act: -0.0001

Data Index: 932823 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0934. Min Act: -0.0001

Data Index: 481516 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0911. Min Act: -0.0001

Data Index: 607962 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1010718 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1015570 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0785. Min Act: -0.0001

Data Index: 968291 (C4 (Web Text))

Max Activating Token Index: 688