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

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

Neuron 3508 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1185351 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.4126. Min Act: -0.0000

Data Index: 859374 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1782. Min Act: -0.0000

Data Index: 911413 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1322745 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1006744 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1029712 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1256. Min Act: 0.0001

Data Index: 678637 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1090. Min Act: -0.0000

Data Index: 680878 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1224. Min Act: -0.0000

Data Index: 700512 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1054. Min Act: 0.0001

Data Index: 1098866 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1042. Min Act: 0.0000

Data Index: 531830 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.1000. Min Act: 0.0000

Data Index: 1161142 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0539. Min Act: -0.0000

Data Index: 548596 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0982. Min Act: -0.0000

Data Index: 718848 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0924. Min Act: 0.0000

Data Index: 716833 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0888. Min Act: -0.0000

Data Index: 217915 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0906. Min Act: 0.0000

Data Index: 1135280 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0876. Min Act: 0.0000

Data Index: 1226024 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0826. Min Act: -0.0000

Data Index: 858154 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.0873. Min Act: -0.0000

Data Index: 830773 (C4 (Web Text))

Max Activating Token Index: 773