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

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

Neuron 3442 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: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0003

Data Index: 1499970 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1650344 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1253. Min Act: -0.0002

Data Index: 1458190 (Python Code)

Max Activating Token Index: 729

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1244. Min Act: -0.0003

Data Index: 1618179 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1158. Min Act: -0.0003

Data Index: 1521227 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1173. Min Act: -0.0003

Data Index: 1541269 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1167. Min Act: -0.0003

Data Index: 1598987 (Python Code)

Max Activating Token Index: 329

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1507849 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1105. Min Act: -0.0003

Data Index: 1565505 (Python Code)

Max Activating Token Index: 322

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1390611 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1087. Min Act: -0.0003

Data Index: 1367701 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1629477 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1520651 (Python Code)

Max Activating Token Index: 428

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1052. Min Act: -0.0003

Data Index: 1426277 (Python Code)

Max Activating Token Index: 434

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1034. Min Act: -0.0003

Data Index: 1539456 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1030. Min Act: -0.0003

Data Index: 1594994 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1029. Min Act: -0.0003

Data Index: 1558463 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1025. Min Act: -0.0003

Data Index: 1606135 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1069. Min Act: -0.0003

Data Index: 1379766 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1436564 (Python Code)

Max Activating Token Index: 642