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

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

Neuron 165 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: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0005

Data Index: 528962 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0880. Min Act: -0.0005

Data Index: 759105 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0899. Min Act: -0.0005

Data Index: 1283510 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0869. Min Act: -0.0005

Data Index: 645511 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0837. Min Act: -0.0005

Data Index: 1096050 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0876. Min Act: -0.0005

Data Index: 968169 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0796. Min Act: -0.0005

Data Index: 188652 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0863. Min Act: -0.0005

Data Index: 421325 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0764. Min Act: -0.0005

Data Index: 729674 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0752. Min Act: -0.0005

Data Index: 147247 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0732. Min Act: -0.0005

Data Index: 1212642 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0730. Min Act: -0.0005

Data Index: 577374 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0745. Min Act: -0.0005

Data Index: 912359 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0743. Min Act: -0.0005

Data Index: 640827 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0712. Min Act: -0.0005

Data Index: 1320123 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0743. Min Act: -0.0005

Data Index: 606557 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0724. Min Act: -0.0005

Data Index: 842151 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0733. Min Act: -0.0005

Data Index: 13570 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0697. Min Act: -0.0005

Data Index: 1053380 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0678. Min Act: -0.0005

Data Index: 771604 (C4 (Web Text))

Max Activating Token Index: 913