Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2002 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0004

Data Index: 1035873 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0843. Min Act: -0.0005

Data Index: 799007 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0843. Min Act: -0.0005

Data Index: 916599 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0823. Min Act: -0.0005

Data Index: 1456336 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0800. Min Act: -0.0005

Data Index: 1260788 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0782. Min Act: -0.0005

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0769. Min Act: -0.0005

Data Index: 46393 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0736. Min Act: -0.0005

Data Index: 292342 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0745. Min Act: -0.0005

Data Index: 605429 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0726. Min Act: -0.0005

Data Index: 1228153 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1429101 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0752. Min Act: -0.0005

Data Index: 1575989 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0761. Min Act: -0.0005

Data Index: 299930 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0685. Min Act: -0.0005

Data Index: 482521 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0762. Min Act: -0.0005

Data Index: 938556 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0733. Min Act: -0.0005

Data Index: 1458065 (Python Code)

Max Activating Token Index: 757

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0795. Min Act: -0.0005

Data Index: 1459205 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0715. Min Act: -0.0005

Data Index: 728148 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0741. Min Act: -0.0005

Data Index: 95935 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0721. Min Act: -0.0005

Data Index: 22580 (C4 (Web Text))

Max Activating Token Index: 662