Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.3429. Min Act: -0.0001

Data Index: 828885 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.2277. Min Act: -0.0001

Data Index: 660225 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1878. Min Act: -0.0001

Data Index: 851579 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1266421 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1267685 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1090768 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1180889 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1846. Min Act: -0.0001

Data Index: 928561 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1907. Min Act: -0.0001

Data Index: 844202 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1933. Min Act: -0.0001

Data Index: 598786 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1062385 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1654. Min Act: -0.0001

Data Index: 916714 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1340697 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1785. Min Act: -0.0001

Data Index: 394514 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1604. Min Act: -0.0001

Data Index: 649901 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1760. Min Act: -0.0001

Data Index: 655120 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1693. Min Act: -0.0001

Data Index: 678450 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1117947 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1736. Min Act: -0.0001

Data Index: 55446 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.3429. Min Range: -0.3429

Max Act: 0.1650. Min Act: -0.0001

Data Index: 791489 (C4 (Web Text))

Max Activating Token Index: 1010