Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1583 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.6789. Min Act: -0.0000

Data Index: 276203 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.3157. Min Act: -0.0000

Data Index: 826767 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.2959. Min Act: -0.0000

Data Index: 310005 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.2162. Min Act: -0.0000

Data Index: 473286 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.2068. Min Act: -0.0000

Data Index: 441185 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.2035. Min Act: -0.0000

Data Index: 906289 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.1841. Min Act: -0.0000

Data Index: 624927 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1266674 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.1665. Min Act: -0.0000

Data Index: 328802 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1328762 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.1398. Min Act: -0.0000

Data Index: 922102 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.1302. Min Act: -0.0000

Data Index: 281776 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1208124 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0392. Min Act: -0.0000

Data Index: 431420 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0341. Min Act: -0.0000

Data Index: 864034 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0353. Min Act: -0.0000

Data Index: 405829 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0974. Min Act: -0.0000

Data Index: 209772 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0801. Min Act: -0.0000

Data Index: 57724 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0766. Min Act: -0.0000

Data Index: 590062 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.6789. Min Range: -1.6789

Max Act: 1.0754. Min Act: -0.0000

Data Index: 979580 (C4 (Web Text))

Max Activating Token Index: 50