Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1967. Min Act: -0.0000

Data Index: 414736 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1455898 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1629. Min Act: -0.0000

Data Index: 589870 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1613. Min Act: -0.0000

Data Index: 840558 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1652085 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1720. Min Act: -0.0000

Data Index: 427604 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1589. Min Act: -0.0000

Data Index: 65934 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1505820 (Python Code)

Max Activating Token Index: 720

Text #8

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1451306 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1607. Min Act: -0.0000

Data Index: 518904 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1633051 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1575. Min Act: -0.0000

Data Index: 665809 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1575. Min Act: -0.0000

Data Index: 636550 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1638889 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1503. Min Act: -0.0000

Data Index: 503590 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1387858 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1538. Min Act: -0.0000

Data Index: 222583 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1529. Min Act: -0.0000

Data Index: 259801 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1607. Min Act: -0.0000

Data Index: 842882 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1504267 (Python Code)

Max Activating Token Index: 476