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

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

Neuron 3217 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: 0.2452. Min Range: -0.2452

Max Act: 0.2452. Min Act: -0.0000

Data Index: 434696 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2042. Min Act: -0.0000

Data Index: 780843 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2164. Min Act: -0.0000

Data Index: 315847 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2200. Min Act: -0.0000

Data Index: 363057 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1118953 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1247099 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1918. Min Act: -0.0000

Data Index: 230755 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1198011 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1084638 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2017. Min Act: -0.0000

Data Index: 208473 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1883. Min Act: -0.0000

Data Index: 760328 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1850. Min Act: -0.0000

Data Index: 679848 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1879. Min Act: -0.0000

Data Index: 181834 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2053. Min Act: -0.0000

Data Index: 239458 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1844. Min Act: -0.0000

Data Index: 999549 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1852. Min Act: -0.0000

Data Index: 447206 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1757. Min Act: -0.0000

Data Index: 951389 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1729. Min Act: -0.0000

Data Index: 2421 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1774. Min Act: -0.0000

Data Index: 964973 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1692. Min Act: -0.0000

Data Index: 918329 (C4 (Web Text))

Max Activating Token Index: 806