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

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

Neuron 4767 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: 0.1326. Min Range: -0.1326

Max Act: 0.1313. Min Act: -0.0000

Data Index: 231993 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1990 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.1326. Min Act: -0.0001

Data Index: 723004 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0916. Min Act: -0.0001

Data Index: 31787 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1329088 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0925. Min Act: -0.0001

Data Index: 553873 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0907. Min Act: -0.0001

Data Index: 370726 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0892. Min Act: -0.0001

Data Index: 738978 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0930. Min Act: -0.0001

Data Index: 691538 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0941. Min Act: -0.0001

Data Index: 209426 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1025245 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0909. Min Act: -0.0001

Data Index: 12219 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1024365 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0879. Min Act: -0.0000

Data Index: 519865 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0781. Min Act: -0.0001

Data Index: 608932 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0833. Min Act: -0.0001

Data Index: 295720 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0861. Min Act: -0.0001

Data Index: 872713 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0809. Min Act: -0.0001

Data Index: 771205 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0801. Min Act: -0.0001

Data Index: 349550 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.1326. Min Range: -0.1326

Max Act: 0.0814. Min Act: -0.0001

Data Index: 915206 (C4 (Web Text))

Max Activating Token Index: 173