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

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

Neuron 5101 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: 0.2375. Min Range: -0.2375

Max Act: 0.2375. Min Act: -0.0000

Data Index: 929289 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2232. Min Act: -0.0000

Data Index: 17689 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2181. Min Act: -0.0000

Data Index: 248228 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2092. Min Act: -0.0000

Data Index: 837445 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1274681 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1325772 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1003043 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1840. Min Act: -0.0000

Data Index: 823417 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2090. Min Act: -0.0000

Data Index: 163085 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1882. Min Act: -0.0000

Data Index: 685868 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1163560 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1156733 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1832. Min Act: -0.0001

Data Index: 391832 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1810. Min Act: -0.0000

Data Index: 550645 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1142592 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1700. Min Act: -0.0000

Data Index: 795862 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1242425 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1853. Min Act: -0.0000

Data Index: 322170 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1114941 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1799. Min Act: -0.0000

Data Index: 178453 (C4 (Web Text))

Max Activating Token Index: 674