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

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

Neuron 360 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.8011. Min Act: -0.0000

Data Index: 1438824 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1551390 (Python Code)

Max Activating Token Index: 543

Text #2

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1492102 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1632250 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1653141 (Python Code)

Max Activating Token Index: 735

Text #5

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1580717 (Python Code)

Max Activating Token Index: 472

Text #6

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1622095 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1512691 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1446430 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1595895 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3958. Min Act: -0.0000

Data Index: 1631816 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1604188 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1459883 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1591446 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1598967 (Python Code)

Max Activating Token Index: 882

Text #15

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1377791 (Python Code)

Max Activating Token Index: 115

Text #16

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1616280 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1406551 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1539346 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1457270 (Python Code)

Max Activating Token Index: 182