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

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

Neuron 3721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.9907. Min Act: -0.0000

Data Index: 917740 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.9348. Min Act: -0.0000

Data Index: 103261 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.9228. Min Act: -0.0000

Data Index: 771896 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.5993. Min Act: -0.0000

Data Index: 648489 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.5322. Min Act: -0.0000

Data Index: 291851 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.4463. Min Act: -0.0000

Data Index: 791258 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1274269 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.4682. Min Act: -0.0000

Data Index: 422105 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.4892. Min Act: -0.0000

Data Index: 251798 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3949. Min Act: -0.0000

Data Index: 554770 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3696. Min Act: -0.0000

Data Index: 316844 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.4363. Min Act: -0.0000

Data Index: 27142 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.4743. Min Act: -0.0000

Data Index: 40876 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1304930 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3910. Min Act: -0.0000

Data Index: 618366 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3772. Min Act: -0.0000

Data Index: 574866 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3958. Min Act: -0.0000

Data Index: 1173624 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3100. Min Act: -0.0000

Data Index: 602085 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3223. Min Act: -0.0000

Data Index: 183651 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 1.9907. Min Range: -1.9907

Max Act: 1.3629. Min Act: -0.0000

Data Index: 874434 (C4 (Web Text))

Max Activating Token Index: 869