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

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

Neuron 575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.2271. Min Act: -0.0001

Data Index: 248727 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1205236 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.2030. Min Act: -0.0001

Data Index: 853867 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1312918 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.2007. Min Act: -0.0001

Data Index: 938020 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.2072. Min Act: -0.0001

Data Index: 9531 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1910. Min Act: -0.0001

Data Index: 268870 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1961. Min Act: -0.0001

Data Index: 1350610 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1948. Min Act: -0.0001

Data Index: 999599 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1856. Min Act: -0.0001

Data Index: 664620 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1863. Min Act: -0.0001

Data Index: 913980 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1962. Min Act: -0.0001

Data Index: 854396 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1107475 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1115586 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1280108 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1819. Min Act: -0.0001

Data Index: 299827 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1901. Min Act: -0.0001

Data Index: 461527 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1856. Min Act: -0.0001

Data Index: 148348 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1242920 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.2271. Min Range: -0.2271

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1199664 (C4 (Web Text))

Max Activating Token Index: 45