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

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

Neuron 5093 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.2095. Min Act: -0.0002

Data Index: 200774 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.2045. Min Act: -0.0002

Data Index: 661423 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1977. Min Act: -0.0002

Data Index: 904470 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1907. Min Act: -0.0002

Data Index: 296840 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1907. Min Act: -0.0002

Data Index: 97407 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1746. Min Act: -0.0002

Data Index: 195531 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1728. Min Act: -0.0002

Data Index: 127093 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1669. Min Act: -0.0002

Data Index: 142458 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1654. Min Act: -0.0002

Data Index: 1302879 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1657. Min Act: -0.0002

Data Index: 763149 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1070530 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1649. Min Act: -0.0002

Data Index: 964287 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1039586 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1613. Min Act: -0.0002

Data Index: 327777 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1578. Min Act: -0.0002

Data Index: 907956 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1560. Min Act: -0.0002

Data Index: 375490 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1569. Min Act: -0.0002

Data Index: 294872 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1548. Min Act: -0.0002

Data Index: 84763 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1557. Min Act: -0.0002

Data Index: 122750 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1512. Min Act: -0.0002

Data Index: 514693 (C4 (Web Text))

Max Activating Token Index: 151