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

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

Neuron 5072 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0081. Min Act: -0.0003

Data Index: 303530 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0076. Min Act: -0.0003

Data Index: 80997 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0077. Min Act: -0.0002

Data Index: 890804 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0077. Min Act: -0.0003

Data Index: 45478 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0076. Min Act: -0.0003

Data Index: 670752 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0077. Min Act: -0.0003

Data Index: 844339 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0072. Min Act: -0.0003

Data Index: 101052 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1251560 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0072. Min Act: -0.0003

Data Index: 705026 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0072. Min Act: -0.0003

Data Index: 548879 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0002

Data Index: 1015452 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0069. Min Act: -0.0002

Data Index: 568253 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1044945 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1203082 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0003

Data Index: 925406 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0002

Data Index: 17125 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1095923 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0068. Min Act: -0.0003

Data Index: 388365 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0071. Min Act: -0.0003

Data Index: 724088 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0081. Min Range: -0.0081

Max Act: 0.0069. Min Act: -0.0003

Data Index: 260459 (C4 (Web Text))

Max Activating Token Index: 92