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

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

Neuron 3410 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1051081 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1036. Min Act: -0.0000

Data Index: 340580 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0000. Min Act: -0.0000

Data Index: 8151 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1206391 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9241. Min Act: -0.0000

Data Index: 370822 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1097128 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8706. Min Act: -0.0000

Data Index: 432100 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9023. Min Act: -0.0000

Data Index: 990557 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8362. Min Act: -0.0000

Data Index: 69030 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8910. Min Act: -0.0000

Data Index: 195621 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9048. Min Act: -0.0000

Data Index: 209793 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8416. Min Act: -0.0000

Data Index: 405781 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7589. Min Act: -0.0000

Data Index: 504752 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7603. Min Act: -0.0000

Data Index: 438874 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7836. Min Act: -0.0000

Data Index: 892241 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8024. Min Act: -0.0000

Data Index: 248395 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7920. Min Act: -0.0000

Data Index: 52147 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7075. Min Act: -0.0000

Data Index: 266791 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1192272 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7574. Min Act: -0.0000

Data Index: 859939 (C4 (Web Text))

Max Activating Token Index: 320