Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1970 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1038837 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1904. Min Act: -0.0001

Data Index: 671372 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1759. Min Act: -0.0001

Data Index: 708476 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2031. Min Act: -0.0001

Data Index: 104931 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1933. Min Act: -0.0001

Data Index: 72558 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1833. Min Act: -0.0001

Data Index: 713361 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1221498 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1738. Min Act: -0.0001

Data Index: 572103 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1052180 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1111961 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1896. Min Act: -0.0001

Data Index: 440115 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1810. Min Act: -0.0001

Data Index: 4129 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1843. Min Act: -0.0001

Data Index: 831318 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1785. Min Act: -0.0001

Data Index: 37217 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1775. Min Act: -0.0001

Data Index: 712035 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1803. Min Act: -0.0001

Data Index: 499573 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1089760 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1781. Min Act: -0.0001

Data Index: 334189 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1720. Min Act: -0.0001

Data Index: 130226 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1032771 (C4 (Web Text))

Max Activating Token Index: 12