Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1798 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1013115 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0969. Min Act: -0.0002

Data Index: 769138 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1028. Min Act: -0.0002

Data Index: 714864 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0998. Min Act: -0.0002

Data Index: 874564 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0892. Min Act: -0.0002

Data Index: 444503 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1114967 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0892. Min Act: -0.0002

Data Index: 426002 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0889. Min Act: -0.0002

Data Index: 301433 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0885. Min Act: -0.0002

Data Index: 559853 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0859. Min Act: -0.0002

Data Index: 832130 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0980. Min Act: -0.0002

Data Index: 750526 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1359203 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0850. Min Act: -0.0002

Data Index: 915396 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0879. Min Act: -0.0002

Data Index: 548835 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0896. Min Act: -0.0002

Data Index: 601193 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0835. Min Act: -0.0002

Data Index: 648731 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0853. Min Act: -0.0002

Data Index: 648999 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0859. Min Act: -0.0002

Data Index: 498378 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1186499 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0832. Min Act: -0.0002

Data Index: 395782 (C4 (Web Text))

Max Activating Token Index: 811