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

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

Neuron 3369 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1412668 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1648808 (Python Code)

Max Activating Token Index: 786

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1375770 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1627195 (Python Code)

Max Activating Token Index: 117

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1474909 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1430521 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1431865 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1498334 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1631276 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1592701 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1571268 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1389091 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1489455 (Python Code)

Max Activating Token Index: 307

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1425432 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1399140 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1604343 (Python Code)

Max Activating Token Index: 807

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1532012 (Python Code)

Max Activating Token Index: 500

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1567665 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1455702 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1607239 (Python Code)

Max Activating Token Index: 902