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

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

Neuron 3965 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0000

Data Index: 197113 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0961. Min Act: -0.0000

Data Index: 680850 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1041520 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0993. Min Act: -0.0000

Data Index: 897732 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0968. Min Act: -0.0000

Data Index: 752965 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1146278 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0888. Min Act: -0.0000

Data Index: 143220 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0946. Min Act: -0.0000

Data Index: 248055 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1167347 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0919. Min Act: -0.0000

Data Index: 996533 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1008080 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0852. Min Act: -0.0000

Data Index: 768483 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0863. Min Act: -0.0000

Data Index: 433652 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0828. Min Act: -0.0000

Data Index: 525434 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1053403 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1174256 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0812. Min Act: -0.0000

Data Index: 335623 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0804. Min Act: -0.0000

Data Index: 433486 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0819. Min Act: -0.0000

Data Index: 898408 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1264602 (C4 (Web Text))

Max Activating Token Index: 213