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

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

Neuron 662 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1606. Min Act: -0.0000

Data Index: 155170 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1032824 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1122363 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1134838 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1216353 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0850. Min Act: -0.0000

Data Index: 730994 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0831. Min Act: -0.0000

Data Index: 695244 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0828. Min Act: -0.0000

Data Index: 469459 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0800. Min Act: -0.0000

Data Index: 790041 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1044690 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0761. Min Act: -0.0000

Data Index: 850712 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0764. Min Act: -0.0000

Data Index: 567006 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0718. Min Act: -0.0000

Data Index: 632647 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1305685 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1656376 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0702. Min Act: -0.0000

Data Index: 845245 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0692. Min Act: -0.0000

Data Index: 112625 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0642. Min Act: -0.0000

Data Index: 608247 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0639. Min Act: -0.0000

Data Index: 422142 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.0668. Min Act: -0.0000

Data Index: 148751 (C4 (Web Text))

Max Activating Token Index: 865