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

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

Neuron 326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1558954 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0001

Data Index: 378502 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1048563 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1218208 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1604759 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0739. Min Act: -0.0001

Data Index: 520097 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1412611 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0624. Min Act: -0.0001

Data Index: 573473 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1533538 (Python Code)

Max Activating Token Index: 373

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1534825 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1448803 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0629. Min Act: -0.0001

Data Index: 926911 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1462991 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1433910 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1383679 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0675. Min Act: -0.0001

Data Index: 1586335 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1012794 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1623582 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1627907 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1450728 (Python Code)

Max Activating Token Index: 468