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

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

Neuron 880 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: 1.4047. Min Range: -1.4047

Max Act: 1.4047. Min Act: -0.0002

Data Index: 137031 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.2855. Min Act: -0.0002

Data Index: 715042 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.2246. Min Act: -0.0002

Data Index: 601963 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.2840. Min Act: -0.0002

Data Index: 1227446 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.2410. Min Act: -0.0002

Data Index: 333798 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1725. Min Act: -0.0002

Data Index: 796668 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1970. Min Act: -0.0002

Data Index: 1124462 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1865. Min Act: -0.0002

Data Index: 191690 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.2054. Min Act: -0.0002

Data Index: 465044 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1908. Min Act: -0.0002

Data Index: 282905 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1847. Min Act: -0.0002

Data Index: 500421 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1479. Min Act: -0.0002

Data Index: 682049 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1580. Min Act: -0.0002

Data Index: 1290266 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1543. Min Act: -0.0002

Data Index: 370256 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1649. Min Act: -0.0002

Data Index: 620542 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1913. Min Act: -0.0002

Data Index: 54193 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1001. Min Act: -0.0002

Data Index: 143615 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1679. Min Act: -0.0002

Data Index: 576290 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.1721. Min Act: -0.0002

Data Index: 176725 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.4047. Min Range: -1.4047

Max Act: 1.0714. Min Act: -0.0002

Data Index: 115314 (C4 (Web Text))

Max Activating Token Index: 187