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

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

Neuron 2528 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0003

Data Index: 477801 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0795. Min Act: -0.0003

Data Index: 205735 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0781. Min Act: -0.0003

Data Index: 5720 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1315563 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0746. Min Act: -0.0003

Data Index: 258850 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0719. Min Act: -0.0003

Data Index: 856849 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1124345 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1096730 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0710. Min Act: -0.0003

Data Index: 24961 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0711. Min Act: -0.0003

Data Index: 818103 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0691. Min Act: -0.0003

Data Index: 856870 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0688. Min Act: -0.0003

Data Index: 804040 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0673. Min Act: -0.0003

Data Index: 842300 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0714. Min Act: -0.0003

Data Index: 881289 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0625. Min Act: -0.0003

Data Index: 963220 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0648. Min Act: -0.0002

Data Index: 826762 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0686. Min Act: -0.0003

Data Index: 424265 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0640. Min Act: -0.0003

Data Index: 461553 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0636. Min Act: -0.0003

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0650. Min Act: -0.0003

Data Index: 56529 (C4 (Web Text))

Max Activating Token Index: 465