Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0003

Data Index: 462810 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1036. Min Act: -0.0003

Data Index: 356554 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0954. Min Act: -0.0003

Data Index: 641707 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0895. Min Act: -0.0003

Data Index: 510814 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1025354 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1263813 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0835. Min Act: -0.0003

Data Index: 410941 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0924. Min Act: -0.0003

Data Index: 481156 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1312659 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1053743 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0859. Min Act: -0.0003

Data Index: 192498 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0849. Min Act: -0.0003

Data Index: 784527 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0876. Min Act: -0.0003

Data Index: 333200 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1183953 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0776. Min Act: -0.0003

Data Index: 1164312 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0827. Min Act: -0.0003

Data Index: 18013 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1121796 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1293305 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0881. Min Act: -0.0003

Data Index: 511953 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1154552 (C4 (Web Text))

Max Activating Token Index: 273