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

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

Neuron 4583 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: 0.2566. Min Range: -0.2566

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1435587 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1491473 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1541875 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1378602 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1644307 (Python Code)

Max Activating Token Index: 327

Text #5

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1548315 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1378930 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1495749 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1605396 (Python Code)

Max Activating Token Index: 535

Text #9

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1535244 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1622978 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1407017 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1568107 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1385510 (Python Code)

Max Activating Token Index: 1021

Text #14

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1383798 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1588. Min Act: 0.0000

Data Index: 1396097 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1460. Min Act: 0.0000

Data Index: 1638735 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1424098 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1484299 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 0.2566. Min Range: -0.2566

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1619175 (Python Code)

Max Activating Token Index: 949