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

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

Neuron 2226 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: 0.2673. Min Range: -0.2673

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1095077 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1345375 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2673. Min Act: -0.0001

Data Index: 386836 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1117731 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2124. Min Act: -0.0001

Data Index: 229985 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1133441 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1938. Min Act: -0.0001

Data Index: 971926 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1812. Min Act: -0.0001

Data Index: 469220 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1935. Min Act: -0.0001

Data Index: 489000 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1926. Min Act: -0.0001

Data Index: 376776 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1944. Min Act: -0.0001

Data Index: 954152 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1654. Min Act: -0.0001

Data Index: 184044 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1055901 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2002. Min Act: -0.0001

Data Index: 27243 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1805. Min Act: -0.0001

Data Index: 504490 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1865. Min Act: -0.0001

Data Index: 707836 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1800. Min Act: -0.0001

Data Index: 321575 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1697. Min Act: -0.0001

Data Index: 442346 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1038362 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.1821. Min Act: -0.0001

Data Index: 879294 (C4 (Web Text))

Max Activating Token Index: 25