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

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

Neuron 1722 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2219. Min Act: -0.0001

Data Index: 399828 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2136. Min Act: -0.0001

Data Index: 326383 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2122. Min Act: -0.0001

Data Index: 59106 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2112. Min Act: -0.0001

Data Index: 171417 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1958. Min Act: -0.0001

Data Index: 954972 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1108239 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1964. Min Act: -0.0001

Data Index: 439073 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2023. Min Act: -0.0001

Data Index: 767507 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1214073 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1955. Min Act: -0.0001

Data Index: 280936 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1924. Min Act: -0.0001

Data Index: 769274 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1037793 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2001. Min Act: -0.0001

Data Index: 990135 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1914. Min Act: -0.0001

Data Index: 917664 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1964. Min Act: -0.0001

Data Index: 781116 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1862. Min Act: -0.0001

Data Index: 554837 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1880. Min Act: -0.0001

Data Index: 155234 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1850. Min Act: -0.0001

Data Index: 124479 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1572700 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1834. Min Act: -0.0001

Data Index: 434774 (C4 (Web Text))

Max Activating Token Index: 628