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

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

Neuron 2068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.3556. Min Act: -0.0000

Data Index: 631427 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.2164. Min Act: -0.0000

Data Index: 488260 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.3322. Min Act: -0.0000

Data Index: 997777 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.0987. Min Act: -0.0000

Data Index: 1232446 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.1728. Min Act: -0.0000

Data Index: 440876 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.2987. Min Act: -0.0000

Data Index: 400129 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.1909. Min Act: -0.0000

Data Index: 438604 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.2766. Min Act: -0.0000

Data Index: 301719 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.1134. Min Act: -0.0000

Data Index: 547272 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.0381. Min Act: -0.0000

Data Index: 244589 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 2.3556. Min Range: -2.3556

Max Act: 1.9159. Min Act: -0.0000

Data Index: 88241 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.0044. Min Act: -0.0000

Data Index: 1045540 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.1106. Min Act: -0.0000

Data Index: 162511 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 2.3556. Min Range: -2.3556

Max Act: 1.8273. Min Act: -0.0000

Data Index: 653396 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.0317. Min Act: -0.0000

Data Index: 948149 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 2.3556. Min Range: -2.3556

Max Act: 1.9040. Min Act: -0.0000

Data Index: 173540 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 2.3556. Min Range: -2.3556

Max Act: 2.0057. Min Act: -0.0000

Data Index: 368827 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 2.3556. Min Range: -2.3556

Max Act: 1.8736. Min Act: -0.0000

Data Index: 510573 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 2.3556. Min Range: -2.3556

Max Act: 1.8801. Min Act: -0.0000

Data Index: 184809 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 2.3556. Min Range: -2.3556

Max Act: 1.8325. Min Act: -0.0000

Data Index: 220794 (C4 (Web Text))

Max Activating Token Index: 949