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

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

Neuron 1833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2376. Min Act: -0.0001

Data Index: 643247 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2670. Min Act: -0.0001

Data Index: 417515 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2540. Min Act: -0.0001

Data Index: 551360 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2180. Min Act: -0.0001

Data Index: 580079 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2110. Min Act: -0.0001

Data Index: 550230 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2144. Min Act: -0.0001

Data Index: 852818 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2050. Min Act: -0.0001

Data Index: 1313778 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2037. Min Act: -0.0001

Data Index: 20476 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1999. Min Act: -0.0001

Data Index: 31871 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2002. Min Act: -0.0001

Data Index: 511820 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1950. Min Act: -0.0001

Data Index: 287454 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1983. Min Act: -0.0001

Data Index: 376743 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1937. Min Act: -0.0001

Data Index: 373755 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1993. Min Act: -0.0001

Data Index: 1274074 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1905. Min Act: -0.0001

Data Index: 773355 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1044326 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1890. Min Act: -0.0001

Data Index: 749525 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1745. Min Act: -0.0001

Data Index: 686359 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1129011 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1734. Min Act: -0.0001

Data Index: 573767 (C4 (Web Text))

Max Activating Token Index: 915