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

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

Neuron 4923 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2351. Min Act: -0.0001

Data Index: 1644443 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1592031 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1454013 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1542778 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1565567 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1783. Min Act: -0.0001

Data Index: 676328 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1643916 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2075. Min Act: -0.0001

Data Index: 1622221 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1494514 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1525776 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1552971 (Python Code)

Max Activating Token Index: 380

Text #11

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1541990 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1365746 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1618236 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1492400 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1510503 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1378327 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1428942 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1412595 (Python Code)

Max Activating Token Index: 416

Text #19

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1475728 (Python Code)

Max Activating Token Index: 129