Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3338 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1269. Min Act: -0.0001

Data Index: 971896 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1225. Min Act: -0.0000

Data Index: 156088 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1120. Min Act: -0.0000

Data Index: 626868 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1162. Min Act: -0.0000

Data Index: 548749 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1091. Min Act: -0.0000

Data Index: 577134 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1062752 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1083. Min Act: -0.0000

Data Index: 940716 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1244079 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1049. Min Act: -0.0000

Data Index: 226012 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1043. Min Act: -0.0000

Data Index: 196219 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1476234 (Python Code)

Max Activating Token Index: 896

Text #11

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1034. Min Act: -0.0001

Data Index: 648112 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1126511 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1458309 (Python Code)

Max Activating Token Index: 467

Text #14

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1012. Min Act: -0.0000

Data Index: 645907 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0989. Min Act: -0.0000

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1162051 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1002. Min Act: -0.0001

Data Index: 561776 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0923. Min Act: -0.0000

Data Index: 64378 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0961. Min Act: -0.0000

Data Index: 768000 (C4 (Web Text))

Max Activating Token Index: 978