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

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

Neuron 2903 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1248762 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.1468. Min Act: -0.0000

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1322780 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.0358. Min Act: -0.0000

Data Index: 63784 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9255. Min Act: -0.0000

Data Index: 544770 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1033584 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8915. Min Act: -0.0000

Data Index: 609726 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8881. Min Act: -0.0000

Data Index: 160277 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9017. Min Act: -0.0000

Data Index: 482474 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9579. Min Act: -0.0000

Data Index: 575762 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8350. Min Act: -0.0000

Data Index: 378320 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7820. Min Act: -0.0000

Data Index: 706137 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7068. Min Act: -0.0000

Data Index: 598784 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7414. Min Act: -0.0000

Data Index: 917892 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7806. Min Act: -0.0000

Data Index: 744258 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1130553 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7284. Min Act: -0.0000

Data Index: 102360 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1223125 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.6887. Min Act: -0.0000

Data Index: 513031 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1077676 (C4 (Web Text))

Max Activating Token Index: 235