Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 703 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0003

Data Index: 419887 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1004175 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0819. Min Act: -0.0004

Data Index: 395794 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1013465 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0750. Min Act: -0.0003

Data Index: 943114 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1225698 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0757. Min Act: -0.0004

Data Index: 520492 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0758. Min Act: -0.0003

Data Index: 639053 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0740. Min Act: -0.0003

Data Index: 1055687 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0721. Min Act: -0.0003

Data Index: 205074 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0738. Min Act: -0.0003

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0737. Min Act: -0.0003

Data Index: 292313 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0735. Min Act: -0.0002

Data Index: 656974 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0729. Min Act: -0.0003

Data Index: 594368 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0724. Min Act: -0.0003

Data Index: 221918 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0703. Min Act: -0.0003

Data Index: 881061 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1553564 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0748. Min Act: -0.0004

Data Index: 1440588 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0711. Min Act: -0.0002

Data Index: 830920 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1306135 (C4 (Web Text))

Max Activating Token Index: 832