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

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

Neuron 1425 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1384442 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1435466 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.0826. Min Act: -0.0000

Data Index: 664327 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1578711 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.0216. Min Act: -0.0000

Data Index: 726296 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1446747 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1501094 (Python Code)

Max Activating Token Index: 755

Text #7

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1377217 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1434577 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1545429 (Python Code)

Max Activating Token Index: 482

Text #10

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9360. Min Act: -0.0000

Data Index: 8693 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.1678. Min Range: -1.1678

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1153444 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1630499 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1640294 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1532575 (Python Code)

Max Activating Token Index: 936

Text #15

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1342550 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1566892 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1268542 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1617097 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 1.1678. Min Range: -1.1678

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1594774 (Python Code)

Max Activating Token Index: 977