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

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

Neuron 4973 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: 0.0999. Min Range: -0.0999

Max Act: 0.0999. Min Act: -0.0002

Data Index: 454166 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0935. Min Act: -0.0002

Data Index: 81989 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0885. Min Act: -0.0002

Data Index: 790932 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1292946 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1340245 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0796. Min Act: -0.0002

Data Index: 435269 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0825. Min Act: -0.0002

Data Index: 902103 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0824. Min Act: -0.0002

Data Index: 760719 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0783. Min Act: -0.0002

Data Index: 665423 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0803. Min Act: -0.0002

Data Index: 419095 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0802. Min Act: -0.0002

Data Index: 397692 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0775. Min Act: -0.0002

Data Index: 663631 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0800. Min Act: -0.0002

Data Index: 296697 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1110818 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1109207 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0756. Min Act: -0.0002

Data Index: 20754 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0727. Min Act: -0.0002

Data Index: 507607 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1081563 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0744. Min Act: -0.0002

Data Index: 426960 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1131810 (C4 (Web Text))

Max Activating Token Index: 177