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

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

Neuron 3456 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0563. Min Act: -0.0000

Data Index: 1078404 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.2716. Min Act: -0.0000

Data Index: 1040610 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.8285. Min Act: -0.0000

Data Index: 987288 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.7782. Min Act: -0.0000

Data Index: 947234 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1229794 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.6346. Min Act: -0.0000

Data Index: 952721 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.6311. Min Act: -0.0000

Data Index: 824535 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.6083. Min Act: -0.0000

Data Index: 893445 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.6096. Min Act: -0.0000

Data Index: 668637 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1256819 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5630. Min Act: -0.0000

Data Index: 512578 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1255466 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.3921. Min Act: -0.0000

Data Index: 823780 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5145. Min Act: -0.0000

Data Index: 1130521 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5150. Min Act: -0.0000

Data Index: 272582 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5211. Min Act: -0.0000

Data Index: 400194 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5128. Min Act: -0.0000

Data Index: 397902 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.5063. Min Act: -0.0000

Data Index: 871969 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.4956. Min Act: -0.0000

Data Index: 369707 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 3.0563. Min Range: -3.0563

Max Act: 1.4800. Min Act: -0.0000

Data Index: 399039 (C4 (Web Text))

Max Activating Token Index: 951