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

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

Neuron 2504 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1534374 (Python Code)

Max Activating Token Index: 1010

Text #1

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1637035 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1395311 (Python Code)

Max Activating Token Index: 528

Text #3

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5926. Min Act: -0.0000

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1649477 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1524631 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1621974 (Python Code)

Max Activating Token Index: 641

Text #7

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1581322 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1380106 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5622. Min Act: -0.0000

Data Index: 300802 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1555836 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1446153 (Python Code)

Max Activating Token Index: 566

Text #12

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5749. Min Act: -0.0000

Data Index: 890671 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1573154 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5917. Min Act: -0.0000

Data Index: 678001 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5003. Min Act: -0.0000

Data Index: 776576 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5667. Min Act: -0.0000

Data Index: 525075 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1401951 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1487801 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.4365. Min Act: 0.0000

Data Index: 885113 (C4 (Web Text))

Max Activating Token Index: 943