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

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

Neuron 93 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: 0.3739. Min Range: -0.3739

Max Act: 0.3739. Min Act: -0.0000

Data Index: 504279 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3572. Min Act: -0.0000

Data Index: 4859 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2869. Min Act: -0.0000

Data Index: 865776 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2408. Min Act: -0.0000

Data Index: 427496 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2369. Min Act: -0.0000

Data Index: 618432 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2264. Min Act: -0.0000

Data Index: 310204 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2416. Min Act: -0.0000

Data Index: 989616 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2154. Min Act: -0.0000

Data Index: 839066 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2298. Min Act: -0.0000

Data Index: 685786 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2281. Min Act: -0.0000

Data Index: 152482 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2059. Min Act: -0.0000

Data Index: 377346 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2151. Min Act: -0.0000

Data Index: 733539 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2125. Min Act: -0.0000

Data Index: 362270 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2200. Min Act: -0.0000

Data Index: 571727 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.1979. Min Act: -0.0000

Data Index: 223296 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.1964. Min Act: -0.0000

Data Index: 218429 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2014. Min Act: -0.0000

Data Index: 364063 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1230413 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1278156 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.1934. Min Act: -0.0000

Data Index: 808411 (C4 (Web Text))

Max Activating Token Index: 218