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

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

Neuron 4730 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2424. Min Act: -0.0001

Data Index: 911794 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2159. Min Act: -0.0001

Data Index: 261163 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1914. Min Act: -0.0001

Data Index: 584708 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2009. Min Act: -0.0001

Data Index: 749992 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1761. Min Act: -0.0001

Data Index: 571052 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1922. Min Act: -0.0001

Data Index: 437283 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1991. Min Act: -0.0001

Data Index: 263511 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1836. Min Act: -0.0001

Data Index: 689998 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1889. Min Act: -0.0001

Data Index: 874936 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1341966 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1811. Min Act: -0.0001

Data Index: 184490 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1094193 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2010. Min Act: -0.0001

Data Index: 496358 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1227068 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1785. Min Act: -0.0001

Data Index: 719305 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1789. Min Act: -0.0001

Data Index: 412336 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1734. Min Act: -0.0001

Data Index: 892690 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1760. Min Act: -0.0001

Data Index: 123779 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1737. Min Act: -0.0001

Data Index: 877084 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1607. Min Act: -0.0001

Data Index: 369640 (C4 (Web Text))

Max Activating Token Index: 773