Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8556. Min Act: -0.0000

Data Index: 365636 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1292197 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.6416. Min Act: -0.0000

Data Index: 30973 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.6023. Min Act: -0.0000

Data Index: 519938 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.6174. Min Act: -0.0000

Data Index: 903897 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5807. Min Act: -0.0000

Data Index: 737634 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.6647. Min Act: -0.0000

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1240978 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.6004. Min Act: -0.0000

Data Index: 240281 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5434. Min Act: -0.0000

Data Index: 218672 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5756. Min Act: -0.0001

Data Index: 20000 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1168741 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.6097. Min Act: -0.0001

Data Index: 694977 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5297. Min Act: -0.0000

Data Index: 512887 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5799. Min Act: -0.0000

Data Index: 403570 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1289698 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5510. Min Act: -0.0000

Data Index: 622428 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5568. Min Act: -0.0000

Data Index: 240874 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1029993 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.8556. Min Range: -0.8556

Max Act: 0.5184. Min Act: -0.0000

Data Index: 927508 (C4 (Web Text))

Max Activating Token Index: 116