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

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

Neuron 4418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8165. Min Range: -2.8165

Max Act: 2.8165. Min Act: -0.0000

Data Index: 1514342 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 2.8165. Min Range: -2.8165

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1507226 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 2.8165. Min Range: -2.8165

Max Act: 2.0489. Min Act: -0.0000

Data Index: 1367672 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.9584. Min Act: -0.0000

Data Index: 1631778 (Python Code)

Max Activating Token Index: 564

Text #4

Max Range: 2.8165. Min Range: -2.8165

Max Act: 2.0202. Min Act: -0.0000

Data Index: 1612513 (Python Code)

Max Activating Token Index: 1017

Text #5

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.8512. Min Act: -0.0000

Data Index: 1424617 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1415918 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.7277. Min Act: -0.0000

Data Index: 1374171 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1408808 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1413314 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1529937 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1492276 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.6723. Min Act: -0.0000

Data Index: 1523816 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1446616 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1427975 (Python Code)

Max Activating Token Index: 197

Text #15

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.4953. Min Act: -0.0000

Data Index: 1633539 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1649547 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1475890 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1540469 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 2.8165. Min Range: -2.8165

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1508159 (Python Code)

Max Activating Token Index: 520