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

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

Neuron 4043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.2113. Min Act: -0.0000

Data Index: 812600 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.2004. Min Act: -0.0000

Data Index: 725111 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1828. Min Act: -0.0000

Data Index: 530338 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1842. Min Act: -0.0000

Data Index: 584642 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1856. Min Act: -0.0000

Data Index: 84652 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1785. Min Act: -0.0000

Data Index: 631132 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1277282 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1758. Min Act: -0.0001

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1769. Min Act: -0.0000

Data Index: 141691 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1787. Min Act: -0.0000

Data Index: 88112 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1564. Min Act: -0.0000

Data Index: 402018 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1755. Min Act: -0.0000

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1504. Min Act: -0.0000

Data Index: 833839 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1582. Min Act: -0.0000

Data Index: 640490 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1627. Min Act: -0.0000

Data Index: 968480 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1560. Min Act: -0.0000

Data Index: 77378 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1137428 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1524. Min Act: -0.0000

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 585