Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1161888 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0823. Min Act: -0.0002

Data Index: 590096 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0852. Min Act: -0.0002

Data Index: 476724 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1344391 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0705. Min Act: -0.0002

Data Index: 576699 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0834. Min Act: -0.0002

Data Index: 887809 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1245374 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0721. Min Act: -0.0002

Data Index: 134034 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1332390 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0743. Min Act: -0.0002

Data Index: 962779 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0719. Min Act: -0.0002

Data Index: 695539 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0678. Min Act: -0.0002

Data Index: 9183 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0718. Min Act: -0.0002

Data Index: 181941 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0688. Min Act: -0.0002

Data Index: 939132 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1015840 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0654. Min Act: -0.0002

Data Index: 127687 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1242805 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0666. Min Act: -0.0002

Data Index: 136329 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1160448 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1021851 (C4 (Web Text))

Max Activating Token Index: 519