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

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

Neuron 3797 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: 0.1171. Min Range: -0.1171

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1402643 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1578005 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1451376 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1116. Min Act: -0.0002

Data Index: 1654575 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1527753 (Python Code)

Max Activating Token Index: 183

Text #5

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1478546 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1608293 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1618701 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1541798 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1380221 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1426736 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1609222 (Python Code)

Max Activating Token Index: 779

Text #12

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1454211 (Python Code)

Max Activating Token Index: 146

Text #13

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1578773 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1521623 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1585487 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1539944 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1503662 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1428065 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1549089 (Python Code)

Max Activating Token Index: 316