Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.9190. Min Act: -0.0000

Data Index: 522192 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.9057. Min Act: -0.0000

Data Index: 363608 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.9018. Min Act: -0.0000

Data Index: 751448 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8070. Min Act: -0.0000

Data Index: 706603 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8523. Min Act: -0.0000

Data Index: 344787 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.9041. Min Act: -0.0000

Data Index: 707816 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1103264 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1156274 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8530. Min Act: -0.0000

Data Index: 515280 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8447. Min Act: -0.0000

Data Index: 115202 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1190968 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1205347 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1260971 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1011390 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1318141 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8588. Min Act: -0.0000

Data Index: 735793 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1178068 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.7942. Min Act: -0.0000

Data Index: 885197 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1018689 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.9190. Min Range: -0.9190

Max Act: 0.8529. Min Act: -0.0000

Data Index: 428668 (C4 (Web Text))

Max Activating Token Index: 144