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

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

Neuron 3553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.2989. Min Act: -0.0000

Data Index: 296751 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.2759. Min Act: -0.0000

Data Index: 13109 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.2709. Min Act: -0.0000

Data Index: 481987 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.1737. Min Act: -0.0000

Data Index: 682339 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1072957 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.2274. Min Act: -0.0000

Data Index: 638410 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.1202. Min Act: 0.0001

Data Index: 89019 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0953. Min Act: -0.0000

Data Index: 302865 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0354. Min Act: -0.0000

Data Index: 139755 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0284. Min Act: -0.0000

Data Index: 881725 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0575. Min Act: -0.0000

Data Index: 852875 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.2989. Min Range: -1.2989

Max Act: 0.9626. Min Act: -0.0000

Data Index: 837044 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0580. Min Act: -0.0000

Data Index: 186731 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0184. Min Act: -0.0000

Data Index: 726471 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0012. Min Act: -0.0000

Data Index: 348605 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.2989. Min Range: -1.2989

Max Act: 1.0008. Min Act: -0.0000

Data Index: 299717 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.2989. Min Range: -1.2989

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1235879 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.2989. Min Range: -1.2989

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1038205 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 1.2989. Min Range: -1.2989

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1054136 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.2989. Min Range: -1.2989

Max Act: 0.9576. Min Act: -0.0000

Data Index: 244255 (C4 (Web Text))

Max Activating Token Index: 265