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

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

Neuron 4796 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: 1.0048. Min Range: -1.0048

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1227721 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.0048. Min Range: -1.0048

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1329606 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9611. Min Act: -0.0000

Data Index: 123809 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1199902 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8815. Min Act: -0.0000

Data Index: 104736 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9065. Min Act: -0.0000

Data Index: 215087 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8788. Min Act: 0.0000

Data Index: 861024 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1074281 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8229. Min Act: -0.0000

Data Index: 752009 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7759. Min Act: -0.0000

Data Index: 168747 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1322279 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7505. Min Act: 0.0000

Data Index: 590537 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1304932 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1070608 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7583. Min Act: 0.0000

Data Index: 761802 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7401. Min Act: -0.0000

Data Index: 809672 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7875. Min Act: -0.0000

Data Index: 601474 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7403. Min Act: -0.0000

Data Index: 166895 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1165772 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6616. Min Act: -0.0000

Data Index: 262563 (C4 (Web Text))

Max Activating Token Index: 761