Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4938 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1231. Min Act: -0.0000

Data Index: 334908 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1445160 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1415119 (Python Code)

Max Activating Token Index: 873

Text #3

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1572899 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1362985 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1361956 (Python Code)

Max Activating Token Index: 783

Text #6

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1576348 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1544363 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1488738 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1502532 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1607245 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1625027 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1616681 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1585558 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1384944 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1588785 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1604293 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0875. Min Act: -0.0000

Data Index: 800859 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1375946 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0964. Min Act: -0.0000

Data Index: 255517 (C4 (Web Text))

Max Activating Token Index: 749