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

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

Neuron 5647 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2165. Min Act: -0.0000

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2120. Min Act: -0.0000

Data Index: 797239 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.2033. Min Act: -0.0000

Data Index: 567831 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1932. Min Act: -0.0000

Data Index: 895283 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1904. Min Act: -0.0000

Data Index: 321380 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1990. Min Act: -0.0000

Data Index: 464247 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1329134 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1920. Min Act: -0.0000

Data Index: 440871 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1984. Min Act: -0.0000

Data Index: 268582 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1025661 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1836. Min Act: -0.0000

Data Index: 447079 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1902. Min Act: -0.0000

Data Index: 157454 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1891. Min Act: -0.0000

Data Index: 662656 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1748. Min Act: -0.0000

Data Index: 533885 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1843. Min Act: -0.0000

Data Index: 487849 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1785. Min Act: -0.0000

Data Index: 650711 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1256289 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1024013 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1724. Min Act: -0.0000

Data Index: 226531 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.2165. Min Range: -0.2165

Max Act: 0.1702. Min Act: -0.0000

Data Index: 486666 (C4 (Web Text))

Max Activating Token Index: 714