Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3187. Min Act: -0.0001

Data Index: 449355 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2519. Min Act: -0.0001

Data Index: 140831 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2326. Min Act: -0.0001

Data Index: 875453 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2523. Min Act: -0.0001

Data Index: 608852 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1095428 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1070222 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2150. Min Act: -0.0001

Data Index: 828983 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1950. Min Act: -0.0001

Data Index: 190690 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1298747 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1584561 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1819. Min Act: -0.0001

Data Index: 133784 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1622392 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1813. Min Act: -0.0001

Data Index: 723744 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1526651 (Python Code)

Max Activating Token Index: 510

Text #14

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1901. Min Act: -0.0001

Data Index: 952084 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1859. Min Act: -0.0001

Data Index: 475629 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1023396 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1343545 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1049068 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1820. Min Act: -0.0001

Data Index: 108256 (C4 (Web Text))

Max Activating Token Index: 244