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

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

Neuron 6005 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1196. Min Act: -0.0001

Data Index: 820655 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0001

Data Index: 512597 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1611906 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1151. Min Act: -0.0001

Data Index: 426651 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1109265 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0977. Min Act: -0.0001

Data Index: 89385 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1524402 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1091538 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0858. Min Act: -0.0001

Data Index: 605782 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1170757 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1335259 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1490305 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0962. Min Act: -0.0001

Data Index: 184779 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1361264 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0832. Min Act: -0.0001

Data Index: 706903 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0879. Min Act: -0.0001

Data Index: 241911 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1533588 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0783. Min Act: -0.0001

Data Index: 193238 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0859. Min Act: -0.0001

Data Index: 960305 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1553863 (Python Code)

Max Activating Token Index: 100