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

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

Neuron 4733 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 8.6047. Min Range: -8.6047

Max Act: 8.6047. Min Act: -0.0000

Data Index: 733577 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 8.6047. Min Range: -8.6047

Max Act: 7.9629. Min Act: -0.0000

Data Index: 351754 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 8.6047. Min Range: -8.6047

Max Act: 7.7619. Min Act: -0.0000

Data Index: 524108 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 8.6047. Min Range: -8.6047

Max Act: 8.0590. Min Act: -0.0000

Data Index: 282258 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 8.6047. Min Range: -8.6047

Max Act: 7.2018. Min Act: -0.0000

Data Index: 1339858 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 8.6047. Min Range: -8.6047

Max Act: 7.6045. Min Act: -0.0000

Data Index: 738313 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 8.6047. Min Range: -8.6047

Max Act: 7.1863. Min Act: -0.0000

Data Index: 1038813 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 8.6047. Min Range: -8.6047

Max Act: 6.6825. Min Act: -0.0000

Data Index: 488469 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 8.6047. Min Range: -8.6047

Max Act: 6.8159. Min Act: -0.0000

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 8.6047. Min Range: -8.6047

Max Act: 6.6862. Min Act: -0.0000

Data Index: 356776 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 8.6047. Min Range: -8.6047

Max Act: 5.8813. Min Act: -0.0000

Data Index: 397043 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.8416. Min Act: -0.0000

Data Index: 734438 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1045287 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1423699 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0114. Min Act: -0.0000

Data Index: 1451368 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0093. Min Act: -0.0000

Data Index: 1368317 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0092. Min Act: -0.0000

Data Index: 1387732 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0077. Min Act: -0.0000

Data Index: 1536718 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0061. Min Act: -0.0000

Data Index: 49513 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 8.6047. Min Range: -8.6047

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1280055 (C4 (Web Text))

Max Activating Token Index: 928