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

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

Neuron 422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.5869. Min Act: -0.0000

Data Index: 1481922 (Python Code)

Max Activating Token Index: 552

Text #1

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.5191. Min Act: -0.0000

Data Index: 1370039 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2840. Min Act: -0.0000

Data Index: 1464014 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.3395. Min Act: -0.0000

Data Index: 1527257 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1448122 (Python Code)

Max Activating Token Index: 829

Text #5

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1427091 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1082. Min Act: -0.0000

Data Index: 715397 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1431506 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1213360 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1378381 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1207192 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1370359 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1511544 (Python Code)

Max Activating Token Index: 791

Text #13

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0957. Min Act: -0.0000

Data Index: 1589451 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0116. Min Act: -0.0000

Data Index: 826063 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1597743 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1608351 (Python Code)

Max Activating Token Index: 932

Text #17

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1583372 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1626246 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1586654 (Python Code)

Max Activating Token Index: 642