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

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

Neuron 2343 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: 0.1868. Min Range: -0.1868

Max Act: 0.1868. Min Act: -0.0001

Data Index: 771836 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1802. Min Act: -0.0001

Data Index: 956498 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1292898 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1751. Min Act: -0.0001

Data Index: 368867 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1706. Min Act: 0.0001

Data Index: 1275681 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1686. Min Act: -0.0001

Data Index: 503983 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1700. Min Act: -0.0001

Data Index: 523932 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1666. Min Act: 0.0001

Data Index: 934343 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1576. Min Act: -0.0000

Data Index: 728711 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1557. Min Act: -0.0001

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1610. Min Act: 0.0002

Data Index: 63333 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1604. Min Act: -0.0000

Data Index: 55125 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1584. Min Act: -0.0001

Data Index: 804638 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1119276 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1569. Min Act: -0.0001

Data Index: 810921 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1059541 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1590. Min Act: -0.0001

Data Index: 702957 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1541. Min Act: -0.0000

Data Index: 732880 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1548. Min Act: -0.0001

Data Index: 417103 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1550. Min Act: -0.0001

Data Index: 588579 (C4 (Web Text))

Max Activating Token Index: 130