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

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

Neuron 2815 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: 0.0774. Min Range: -0.0774

Max Act: 0.0763. Min Act: -0.0003

Data Index: 947566 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0748. Min Act: -0.0003

Data Index: 123217 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1064115 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0732. Min Act: -0.0003

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0729. Min Act: -0.0003

Data Index: 281763 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0730. Min Act: -0.0003

Data Index: 648984 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0721. Min Act: -0.0003

Data Index: 571707 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0722. Min Act: -0.0003

Data Index: 186254 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0692. Min Act: -0.0003

Data Index: 871133 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0666. Min Act: -0.0003

Data Index: 18742 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1291888 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0003

Data Index: 892159 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0771. Min Act: -0.0003

Data Index: 347457 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0756. Min Act: -0.0003

Data Index: 353861 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1051967 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0721. Min Act: -0.0003

Data Index: 312456 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0720. Min Act: -0.0003

Data Index: 10612 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0691. Min Act: -0.0003

Data Index: 820782 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0725. Min Act: -0.0003

Data Index: 925902 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1340376 (C4 (Web Text))

Max Activating Token Index: 418