Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1915 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0000

Data Index: 615642 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0990. Min Act: -0.0000

Data Index: 121108 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0958. Min Act: -0.0000

Data Index: 792623 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1042959 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0888. Min Act: -0.0000

Data Index: 276270 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0854. Min Act: -0.0000

Data Index: 756376 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0817. Min Act: -0.0000

Data Index: 248185 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0806. Min Act: -0.0000

Data Index: 999024 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0807. Min Act: -0.0000

Data Index: 380188 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0791. Min Act: -0.0000

Data Index: 729743 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1180245 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0788. Min Act: -0.0000

Data Index: 463048 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1043000 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1132713 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0726. Min Act: -0.0000

Data Index: 841547 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1218190 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0754. Min Act: -0.0000

Data Index: 825215 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0757. Min Act: -0.0000

Data Index: 858902 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0695. Min Act: -0.0000

Data Index: 24149 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1122843 (C4 (Web Text))

Max Activating Token Index: 1019