Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1072 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5427. Min Act: -0.0000

Data Index: 420268 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1234680 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5224. Min Act: -0.0000

Data Index: 594756 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4786. Min Act: -0.0000

Data Index: 279874 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5546. Min Act: -0.0000

Data Index: 677069 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5052. Min Act: -0.0000

Data Index: 713585 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4831. Min Act: -0.0000

Data Index: 669706 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4694. Min Act: -0.0000

Data Index: 547946 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4851. Min Act: -0.0000

Data Index: 143911 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1117222 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4701. Min Act: -0.0000

Data Index: 602221 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4692. Min Act: -0.0000

Data Index: 418682 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4578. Min Act: -0.0000

Data Index: 403221 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4637. Min Act: -0.0000

Data Index: 612738 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4628. Min Act: -0.0000

Data Index: 215957 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4707. Min Act: -0.0000

Data Index: 45143 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4537. Min Act: -0.0000

Data Index: 19707 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4342. Min Act: -0.0000

Data Index: 821227 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1125670 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 684