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

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

Neuron 1117 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0002

Data Index: 433439 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0926. Min Act: -0.0002

Data Index: 752516 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0864. Min Act: -0.0002

Data Index: 61671 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0902. Min Act: -0.0002

Data Index: 414656 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1203333 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0880. Min Act: -0.0002

Data Index: 325626 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0845. Min Act: -0.0002

Data Index: 229276 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0816. Min Act: -0.0002

Data Index: 685538 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0823. Min Act: -0.0002

Data Index: 372876 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0793. Min Act: -0.0002

Data Index: 450667 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0813. Min Act: -0.0002

Data Index: 208114 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0784. Min Act: -0.0002

Data Index: 836347 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0773. Min Act: -0.0002

Data Index: 12904 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0767. Min Act: -0.0002

Data Index: 504879 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1120206 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0743. Min Act: -0.0002

Data Index: 703626 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1268447 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0789. Min Act: -0.0002

Data Index: 329000 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1128752 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0738. Min Act: -0.0002

Data Index: 601773 (C4 (Web Text))

Max Activating Token Index: 216