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

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

Neuron 3655 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2919. Min Act: -0.0000

Data Index: 162619 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2729. Min Act: -0.0000

Data Index: 796565 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2527. Min Act: -0.0000

Data Index: 820846 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2581. Min Act: -0.0000

Data Index: 68813 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2563. Min Act: -0.0000

Data Index: 829831 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1208548 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2601. Min Act: -0.0000

Data Index: 643636 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2489. Min Act: -0.0000

Data Index: 901202 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1312289 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2336. Min Act: -0.0000

Data Index: 145043 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1097472 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2390. Min Act: -0.0000

Data Index: 547910 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2221. Min Act: -0.0000

Data Index: 813352 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1269526 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2239. Min Act: -0.0000

Data Index: 776988 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2162. Min Act: -0.0000

Data Index: 573465 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2116. Min Act: -0.0000

Data Index: 151005 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2102. Min Act: -0.0000

Data Index: 434713 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2222. Min Act: -0.0000

Data Index: 503138 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2213. Min Act: -0.0000

Data Index: 413532 (C4 (Web Text))

Max Activating Token Index: 853