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

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

Neuron 394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0000

Data Index: 467324 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0879. Min Act: -0.0000

Data Index: 565757 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0830. Min Act: -0.0000

Data Index: 397835 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0756. Min Act: -0.0000

Data Index: 130825 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1035149 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1005879 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0704. Min Act: -0.0000

Data Index: 689534 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1276712 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0672. Min Act: -0.0000

Data Index: 389912 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0674. Min Act: -0.0000

Data Index: 749095 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0649. Min Act: -0.0000

Data Index: 417033 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0695. Min Act: -0.0000

Data Index: 982542 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1199683 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1428423 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0632. Min Act: -0.0000

Data Index: 678966 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0684. Min Act: -0.0000

Data Index: 958082 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1024131 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1266156 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0603. Min Act: -0.0000

Data Index: 816966 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0648. Min Act: -0.0000

Data Index: 504194 (C4 (Web Text))

Max Activating Token Index: 816