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

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

Neuron 3449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1398122 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1210. Min Act: -0.0002

Data Index: 1429130 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1364458 (Python Code)

Max Activating Token Index: 605

Text #3

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1537867 (Python Code)

Max Activating Token Index: 623

Text #4

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1548287 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1609902 (Python Code)

Max Activating Token Index: 544

Text #6

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1116. Min Act: -0.0002

Data Index: 1528778 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1396960 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1510398 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1444268 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1412838 (Python Code)

Max Activating Token Index: 510

Text #11

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1463240 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1490618 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1392799 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1478376 (Python Code)

Max Activating Token Index: 559

Text #15

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1544337 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1382122 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1556725 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1462231 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1364017 (Python Code)

Max Activating Token Index: 365