Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 98 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1754. Min Act: -0.0000

Data Index: 715934 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1159722 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9826. Min Act: -0.0000

Data Index: 675931 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9616. Min Act: -0.0000

Data Index: 374640 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.8717. Min Act: -0.0000

Data Index: 251098 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.8930. Min Act: -0.0000

Data Index: 726045 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1099052 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.9149. Min Act: -0.0000

Data Index: 719815 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7873. Min Act: -0.0000

Data Index: 381770 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.8045. Min Act: -0.0000

Data Index: 393760 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.8266. Min Act: -0.0000

Data Index: 434472 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7695. Min Act: -0.0000

Data Index: 964663 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7568. Min Act: -0.0000

Data Index: 80097 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1139930 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7027. Min Act: -0.0000

Data Index: 251195 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1134756 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.7294. Min Act: -0.0000

Data Index: 518798 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.6715. Min Act: -0.0000

Data Index: 133401 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.6544. Min Act: -0.0000

Data Index: 436896 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.1754. Min Range: -1.1754

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1398 (C4 (Web Text))

Max Activating Token Index: 529