Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 542 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0005

Data Index: 328788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1223. Min Act: -0.0006

Data Index: 533684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1124. Min Act: -0.0006

Data Index: 1316988 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0921. Min Act: -0.0005

Data Index: 237310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0955. Min Act: -0.0005

Data Index: 945 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0920. Min Act: -0.0006

Data Index: 977570 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0908. Min Act: -0.0005

Data Index: 373684 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0902. Min Act: -0.0006

Data Index: 1057795 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0897. Min Act: -0.0005

Data Index: 943808 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0883. Min Act: -0.0006

Data Index: 238758 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0847. Min Act: -0.0006

Data Index: 942133 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0875. Min Act: -0.0005

Data Index: 137558 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0842. Min Act: -0.0005

Data Index: 1356885 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0838. Min Act: -0.0005

Data Index: 13792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0855. Min Act: -0.0005

Data Index: 534286 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0849. Min Act: -0.0006

Data Index: 368247 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0840. Min Act: -0.0005

Data Index: 347667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0807. Min Act: -0.0006

Data Index: 209974 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0832. Min Act: -0.0005

Data Index: 866660 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0829. Min Act: -0.0005

Data Index: 1329972 (C4 (Web Text))

Max Activating Token Index: 900