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

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

Neuron 3573 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1811. Min Act: -0.0000

Data Index: 213857 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1622891 (Python Code)

Max Activating Token Index: 205

Text #2

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1893. Min Act: -0.0000

Data Index: 429962 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1241278 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1753. Min Act: -0.0000

Data Index: 358830 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1740. Min Act: -0.0000

Data Index: 735852 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1655. Min Act: -0.0000

Data Index: 111170 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1419221 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1797. Min Act: -0.0000

Data Index: 458657 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1147575 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1597. Min Act: -0.0000

Data Index: 588171 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1563. Min Act: -0.0000

Data Index: 266596 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1639. Min Act: -0.0000

Data Index: 366344 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1342188 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1598. Min Act: -0.0000

Data Index: 420715 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1272649 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1549. Min Act: -0.0000

Data Index: 143317 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1529. Min Act: -0.0000

Data Index: 599442 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1534. Min Act: -0.0000

Data Index: 167811 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.1893. Min Range: -0.1893

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1630477 (Python Code)

Max Activating Token Index: 98