Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2126 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4716. Min Act: -0.0003

Data Index: 1516055 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4271. Min Act: -0.0003

Data Index: 1644764 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4481. Min Act: -0.0003

Data Index: 1368791 (Python Code)

Max Activating Token Index: 616

Text #3

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4370. Min Act: -0.0003

Data Index: 1366144 (Python Code)

Max Activating Token Index: 739

Text #4

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4478. Min Act: -0.0003

Data Index: 1540713 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4291. Min Act: -0.0003

Data Index: 1404845 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4270. Min Act: -0.0003

Data Index: 1439315 (Python Code)

Max Activating Token Index: 813

Text #7

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4258. Min Act: -0.0003

Data Index: 1594116 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4118. Min Act: -0.0003

Data Index: 1524411 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3874. Min Act: -0.0003

Data Index: 1492487 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4044. Min Act: -0.0003

Data Index: 1630820 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4121. Min Act: -0.0003

Data Index: 1637984 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4283. Min Act: -0.0003

Data Index: 1426483 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4093. Min Act: -0.0003

Data Index: 1477627 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4237. Min Act: -0.0003

Data Index: 1486450 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4161. Min Act: -0.0003

Data Index: 1426047 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4452. Min Act: -0.0003

Data Index: 1395035 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4092. Min Act: -0.0003

Data Index: 1477975 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3941. Min Act: -0.0003

Data Index: 1584726 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4065. Min Act: -0.0003

Data Index: 1432291 (Python Code)

Max Activating Token Index: 838