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

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

Neuron 3765 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1589277 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0715. Min Act: -0.0000

Data Index: 264352 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1395914 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1563481 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1290775 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0653. Min Act: -0.0000

Data Index: 927834 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1447578 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0604. Min Act: -0.0000

Data Index: 727730 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0588. Min Act: -0.0000

Data Index: 334359 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1505932 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1326936 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1482340 (Python Code)

Max Activating Token Index: 954

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0573. Min Act: -0.0000

Data Index: 276903 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0555. Min Act: -0.0000

Data Index: 252891 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1385221 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0518. Min Act: -0.0000

Data Index: 698879 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0538. Min Act: -0.0000

Data Index: 117955 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1189731 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0545. Min Act: -0.0000

Data Index: 432486 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0562. Min Act: -0.0000

Data Index: 437401 (C4 (Web Text))

Max Activating Token Index: 886