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

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

Neuron 3207 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: 0.7323. Min Range: -0.7323

Max Act: 0.7323. Min Act: -0.0000

Data Index: 685531 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6005. Min Act: -0.0000

Data Index: 498763 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5884. Min Act: -0.0000

Data Index: 823967 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1009064 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5919. Min Act: -0.0000

Data Index: 77688 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6033. Min Act: -0.0000

Data Index: 500829 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6090. Min Act: -0.0000

Data Index: 64316 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5949. Min Act: -0.0000

Data Index: 398037 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1164119 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5443. Min Act: -0.0000

Data Index: 530737 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5885. Min Act: -0.0000

Data Index: 96552 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1259589 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5340. Min Act: -0.0000

Data Index: 45653 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5449. Min Act: -0.0000

Data Index: 889258 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5043. Min Act: -0.0000

Data Index: 81367 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5005. Min Act: -0.0000

Data Index: 619067 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1338050 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4725. Min Act: -0.0000

Data Index: 536757 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4862. Min Act: -0.0000

Data Index: 770939 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4819. Min Act: -0.0000

Data Index: 454715 (C4 (Web Text))

Max Activating Token Index: 537