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

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

Neuron 1686 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1150427 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1168874 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0916. Min Act: -0.0002

Data Index: 16458 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0880. Min Act: -0.0002

Data Index: 782703 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0897. Min Act: -0.0002

Data Index: 776849 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0884. Min Act: -0.0002

Data Index: 818705 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0838. Min Act: -0.0002

Data Index: 491789 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1168416 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0835. Min Act: -0.0002

Data Index: 894808 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0897. Min Act: -0.0002

Data Index: 572810 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0850. Min Act: -0.0002

Data Index: 686734 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1121926 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0883. Min Act: -0.0002

Data Index: 573350 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0707. Min Act: -0.0002

Data Index: 134409 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0881. Min Act: -0.0002

Data Index: 135148 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0850. Min Act: -0.0002

Data Index: 14060 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0826. Min Act: -0.0002

Data Index: 995644 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1278516 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1273839 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1011815 (C4 (Web Text))

Max Activating Token Index: 1004