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

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

Neuron 1879 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2050. Min Act: -0.0000

Data Index: 817275 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1945. Min Act: -0.0000

Data Index: 153354 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1256984 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1819. Min Act: -0.0000

Data Index: 439976 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1314682 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1730. Min Act: -0.0000

Data Index: 721148 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1863. Min Act: -0.0000

Data Index: 732650 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1656. Min Act: -0.0000

Data Index: 126879 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1701. Min Act: -0.0000

Data Index: 75057 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1754. Min Act: -0.0000

Data Index: 197250 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1744. Min Act: -0.0000

Data Index: 411852 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1733. Min Act: -0.0000

Data Index: 26859 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1788. Min Act: -0.0000

Data Index: 457703 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1805. Min Act: -0.0000

Data Index: 183510 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1156366 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1705. Min Act: -0.0000

Data Index: 931017 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1800. Min Act: -0.0000

Data Index: 46065 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1789. Min Act: -0.0000

Data Index: 149036 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1663. Min Act: -0.0000

Data Index: 149060 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1733. Min Act: -0.0000

Data Index: 961254 (C4 (Web Text))

Max Activating Token Index: 244