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

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

Neuron 5972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0000

Data Index: 660440 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1333. Min Act: -0.0000

Data Index: 647361 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1220. Min Act: -0.0000

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1122. Min Act: -0.0000

Data Index: 585454 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1258695 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1022949 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1119. Min Act: -0.0000

Data Index: 204400 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1214. Min Act: -0.0000

Data Index: 239763 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1054. Min Act: -0.0000

Data Index: 713799 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1096. Min Act: -0.0000

Data Index: 350956 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1086. Min Act: -0.0000

Data Index: 950974 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1082. Min Act: -0.0000

Data Index: 89152 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1588415 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1521227 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1120841 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1006753 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0982. Min Act: -0.0000

Data Index: 330873 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1275535 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1411576 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1051. Min Act: -0.0000

Data Index: 402757 (C4 (Web Text))

Max Activating Token Index: 212