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

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

Neuron 3139 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.9783. Min Act: -0.0001

Data Index: 594218 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.9349. Min Act: -0.0001

Data Index: 605673 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6571. Min Act: -0.0001

Data Index: 114350 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6812. Min Act: -0.0001

Data Index: 1009893 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7128. Min Act: -0.0001

Data Index: 327011 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6354. Min Act: -0.0001

Data Index: 397591 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1061646 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6520. Min Act: -0.0001

Data Index: 372111 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1041373 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6325. Min Act: -0.0001

Data Index: 239228 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6306. Min Act: -0.0001

Data Index: 977194 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6310. Min Act: -0.0001

Data Index: 917346 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6297. Min Act: -0.0001

Data Index: 779162 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6021. Min Act: -0.0001

Data Index: 222272 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5648. Min Act: -0.0001

Data Index: 490025 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6330. Min Act: -0.0001

Data Index: 90387 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6120. Min Act: -0.0001

Data Index: 560812 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5896. Min Act: -0.0001

Data Index: 406590 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5431. Min Act: -0.0001

Data Index: 729164 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6030. Min Act: -0.0001

Data Index: 786585 (C4 (Web Text))

Max Activating Token Index: 493