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

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

Neuron 405 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: 0.1972. Min Range: -0.1972

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1383233 (Python Code)

Max Activating Token Index: 501

Text #1

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1871. Min Act: -0.0001

Data Index: 605825 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1634245 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1451577 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1411328 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1161212 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1793. Min Act: 0.0000

Data Index: 1411218 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1592763 (Python Code)

Max Activating Token Index: 169

Text #8

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1633032 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1547720 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1636339 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1603670 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1364953 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1424460 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1487591 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1380256 (Python Code)

Max Activating Token Index: 229

Text #16

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1557. Min Act: -0.0001

Data Index: 534380 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1383783 (Python Code)

Max Activating Token Index: 429

Text #18

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1630637 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1499970 (Python Code)

Max Activating Token Index: 961