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

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

Neuron 4652 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1423591 (Python Code)

Max Activating Token Index: 367

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0002

Data Index: 1513534 (Python Code)

Max Activating Token Index: 387

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1563621 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1416581 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1422537 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1492778 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1475747 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1569318 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1577234 (Python Code)

Max Activating Token Index: 145

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1537304 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1385212 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1514504 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1252. Min Act: -0.0002

Data Index: 1400125 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1510597 (Python Code)

Max Activating Token Index: 522

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1587555 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1503585 (Python Code)

Max Activating Token Index: 917

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1550911 (Python Code)

Max Activating Token Index: 414

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1537157 (Python Code)

Max Activating Token Index: 451

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1525807 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1400484 (Python Code)

Max Activating Token Index: 424