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

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

Neuron 4496 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1141697 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1285158 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0812. Min Act: -0.0000

Data Index: 632155 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1058589 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0770. Min Act: -0.0000

Data Index: 663487 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0791. Min Act: -0.0000

Data Index: 836067 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0782. Min Act: -0.0000

Data Index: 791890 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0748. Min Act: -0.0000

Data Index: 845958 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1357656 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1341643 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0713. Min Act: -0.0000

Data Index: 158567 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0761. Min Act: -0.0000

Data Index: 355788 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0784. Min Act: -0.0000

Data Index: 548651 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0756. Min Act: -0.0000

Data Index: 15440 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0724. Min Act: -0.0000

Data Index: 197741 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1004030 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0727. Min Act: -0.0000

Data Index: 605877 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0721. Min Act: -0.0000

Data Index: 554221 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1020558 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0689. Min Act: -0.0000

Data Index: 525319 (C4 (Web Text))

Max Activating Token Index: 709