Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2579 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3757. Min Act: -0.0001

Data Index: 1038623 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1198686 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1995. Min Act: -0.0001

Data Index: 110450 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2144. Min Act: -0.0000

Data Index: 522499 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1180024 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1825. Min Act: -0.0000

Data Index: 407767 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1911. Min Act: -0.0001

Data Index: 798898 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2040. Min Act: -0.0001

Data Index: 338391 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1899. Min Act: -0.0000

Data Index: 423934 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1836. Min Act: -0.0000

Data Index: 657165 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1168145 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1857. Min Act: -0.0001

Data Index: 761543 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1873. Min Act: -0.0000

Data Index: 658479 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1810. Min Act: -0.0000

Data Index: 651333 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1050951 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1956. Min Act: -0.0001

Data Index: 621460 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1148122 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1075044 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1670. Min Act: -0.0001

Data Index: 904537 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.1856. Min Act: -0.0000

Data Index: 9426 (C4 (Web Text))

Max Activating Token Index: 158