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

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

Neuron 3800 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.8794. Min Act: 0.0000

Data Index: 552387 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.8445. Min Act: -0.0000

Data Index: 581887 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7910. Min Act: -0.0000

Data Index: 517566 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7250. Min Act: -0.0000

Data Index: 402576 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1315386 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6989. Min Act: -0.0000

Data Index: 872802 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1174868 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6785. Min Act: 0.0001

Data Index: 1200680 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1223912 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6762. Min Act: 0.0000

Data Index: 1150933 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6442. Min Act: -0.0000

Data Index: 887032 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6537. Min Act: 0.0000

Data Index: 605855 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6378. Min Act: 0.0000

Data Index: 553310 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6367. Min Act: -0.0000

Data Index: 594890 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6373. Min Act: -0.0000

Data Index: 228239 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6344. Min Act: 0.0001

Data Index: 76501 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6475. Min Act: 0.0000

Data Index: 1213122 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1025336 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6486. Min Act: 0.0000

Data Index: 719743 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6349. Min Act: 0.0001

Data Index: 137350 (C4 (Web Text))

Max Activating Token Index: 296