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

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

Neuron 2041 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0006

Data Index: 1292484 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0894. Min Act: -0.0006

Data Index: 660083 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0006

Data Index: 377816 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0888. Min Act: -0.0006

Data Index: 875371 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0835. Min Act: -0.0006

Data Index: 960255 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0827. Min Act: -0.0006

Data Index: 1241976 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0841. Min Act: -0.0006

Data Index: 484255 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0820. Min Act: -0.0006

Data Index: 990153 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0797. Min Act: -0.0006

Data Index: 1298490 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0782. Min Act: -0.0006

Data Index: 440324 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0792. Min Act: -0.0006

Data Index: 434421 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0804. Min Act: -0.0006

Data Index: 1203338 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0807. Min Act: -0.0006

Data Index: 697666 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0734. Min Act: -0.0006

Data Index: 515074 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0786. Min Act: -0.0006

Data Index: 67716 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0790. Min Act: -0.0006

Data Index: 226173 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0799. Min Act: -0.0006

Data Index: 940644 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0777. Min Act: -0.0006

Data Index: 850109 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0761. Min Act: -0.0006

Data Index: 999636 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0741. Min Act: -0.0006

Data Index: 574841 (C4 (Web Text))

Max Activating Token Index: 429