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

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

Neuron 3149 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: 0.6225. Min Range: -0.6225

Max Act: 0.5944. Min Act: -0.0003

Data Index: 42143 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5925. Min Act: -0.0003

Data Index: 505434 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6225. Min Act: -0.0003

Data Index: 563306 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5811. Min Act: -0.0003

Data Index: 1230143 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5984. Min Act: -0.0003

Data Index: 495999 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5856. Min Act: -0.0003

Data Index: 1268682 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5668. Min Act: -0.0003

Data Index: 745895 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5633. Min Act: -0.0003

Data Index: 937410 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5619. Min Act: -0.0003

Data Index: 785919 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5742. Min Act: -0.0003

Data Index: 778416 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5397. Min Act: -0.0003

Data Index: 1070513 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5499. Min Act: -0.0003

Data Index: 1127437 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5705. Min Act: -0.0003

Data Index: 1244559 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5497. Min Act: -0.0003

Data Index: 787136 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5611. Min Act: -0.0003

Data Index: 966211 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5291. Min Act: -0.0003

Data Index: 205059 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5139. Min Act: -0.0003

Data Index: 998013 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5365. Min Act: -0.0003

Data Index: 401364 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5156. Min Act: -0.0003

Data Index: 715458 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5102. Min Act: -0.0002

Data Index: 795143 (C4 (Web Text))

Max Activating Token Index: 275