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

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

Neuron 891 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: 0.1259. Min Range: -0.1259

Max Act: 0.1259. Min Act: -0.0002

Data Index: 1649752 (Python Code)

Max Activating Token Index: 126

Text #1

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1247. Min Act: -0.0002

Data Index: 1640767 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1403801 (Python Code)

Max Activating Token Index: 78

Text #3

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1525371 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1480559 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1479618 (Python Code)

Max Activating Token Index: 557

Text #6

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1625583 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1435453 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1602586 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1638779 (Python Code)

Max Activating Token Index: 310

Text #10

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1386990 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1421392 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1619905 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1656407 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1614151 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1568800 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1580085 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1528867 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1441973 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1597593 (Python Code)

Max Activating Token Index: 124