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

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

Neuron 5842 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2098. Min Act: -0.0000

Data Index: 324223 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2091. Min Act: -0.0000

Data Index: 173560 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2315. Min Act: -0.0000

Data Index: 3155 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1182325 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1909. Min Act: -0.0000

Data Index: 260802 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2058. Min Act: -0.0000

Data Index: 568713 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1870. Min Act: -0.0000

Data Index: 75159 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1974. Min Act: -0.0000

Data Index: 264798 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1889. Min Act: -0.0000

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1861. Min Act: -0.0000

Data Index: 281611 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1178779 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1776. Min Act: -0.0000

Data Index: 505797 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1971. Min Act: -0.0000

Data Index: 217350 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1956. Min Act: -0.0000

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1807. Min Act: -0.0000

Data Index: 999506 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1162231 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1791. Min Act: -0.0000

Data Index: 563198 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1917. Min Act: -0.0000

Data Index: 396662 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1897. Min Act: -0.0000

Data Index: 989729 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1199182 (C4 (Web Text))

Max Activating Token Index: 37