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

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

Neuron 5749 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0996. Min Act: -0.0002

Data Index: 26606 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.1022. Min Act: -0.0002

Data Index: 626722 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0912. Min Act: -0.0002

Data Index: 766882 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0901. Min Act: -0.0002

Data Index: 440682 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0869. Min Act: -0.0002

Data Index: 795484 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0873. Min Act: -0.0002

Data Index: 550696 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0790. Min Act: -0.0002

Data Index: 163927 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0830. Min Act: -0.0002

Data Index: 307146 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0791. Min Act: -0.0002

Data Index: 2439 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0791. Min Act: -0.0002

Data Index: 342591 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0779. Min Act: -0.0002

Data Index: 735983 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1224341 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0811. Min Act: -0.0002

Data Index: 101514 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0785. Min Act: -0.0002

Data Index: 444118 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0751. Min Act: -0.0002

Data Index: 675460 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0776. Min Act: -0.0002

Data Index: 933092 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0741. Min Act: -0.0002

Data Index: 926256 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1050691 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0762. Min Act: -0.0002

Data Index: 95897 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1048857 (C4 (Web Text))

Max Activating Token Index: 194