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

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

Neuron 4696 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1332523 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6591. Min Act: -0.0000

Data Index: 769518 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5544. Min Act: -0.0000

Data Index: 910676 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6183. Min Act: -0.0000

Data Index: 576267 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6147. Min Act: -0.0000

Data Index: 435788 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5843. Min Act: -0.0000

Data Index: 837139 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1115675 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5969. Min Act: -0.0000

Data Index: 525050 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5927. Min Act: -0.0000

Data Index: 363335 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5357. Min Act: -0.0000

Data Index: 362284 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5545. Min Act: -0.0000

Data Index: 638409 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5706. Min Act: -0.0000

Data Index: 999110 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1037544 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4899. Min Act: -0.0000

Data Index: 670709 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1103996 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1244467 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1045699 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5412. Min Act: -0.0000

Data Index: 632817 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1004409 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5383. Min Act: -0.0000

Data Index: 168447 (C4 (Web Text))

Max Activating Token Index: 746