Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1990 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0885. Min Act: -0.0003

Data Index: 717478 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0890. Min Act: -0.0003

Data Index: 495175 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0894. Min Act: -0.0003

Data Index: 196593 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0003

Data Index: 331568 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0867. Min Act: -0.0003

Data Index: 662328 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0839. Min Act: -0.0003

Data Index: 657611 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0829. Min Act: -0.0003

Data Index: 794234 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0783. Min Act: -0.0003

Data Index: 117344 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0756. Min Act: -0.0003

Data Index: 895134 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1077982 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0810. Min Act: -0.0003

Data Index: 219959 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0788. Min Act: -0.0004

Data Index: 423760 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0828. Min Act: -0.0004

Data Index: 1096944 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0823. Min Act: -0.0003

Data Index: 452678 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0794. Min Act: -0.0003

Data Index: 592058 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0778. Min Act: -0.0003

Data Index: 333799 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0777. Min Act: -0.0003

Data Index: 270069 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1116558 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1268103 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0735. Min Act: -0.0003

Data Index: 420603 (C4 (Web Text))

Max Activating Token Index: 675