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

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

Neuron 5350 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: 0.1155. Min Range: -0.1155

Max Act: 0.1155. Min Act: -0.0002

Data Index: 325892 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1168599 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1468079 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1538776 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1097. Min Act: -0.0002

Data Index: 153122 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1483268 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1571055 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1557278 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1071. Min Act: -0.0002

Data Index: 1521655 (Python Code)

Max Activating Token Index: 891

Text #9

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1570174 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1534318 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1057. Min Act: -0.0002

Data Index: 517783 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1471773 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1581054 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1062. Min Act: -0.0002

Data Index: 751159 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1031. Min Act: -0.0002

Data Index: 440622 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1370941 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1409172 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1428296 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1637642 (Python Code)

Max Activating Token Index: 724