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

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

Neuron 3140 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: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0000

Data Index: 602617 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1425293 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1647551 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1023477 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6794. Min Act: -0.0000

Data Index: 334000 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6166. Min Act: -0.0000

Data Index: 326486 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1580351 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6780. Min Act: -0.0000

Data Index: 911335 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6373. Min Act: -0.0000

Data Index: 115053 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6278. Min Act: -0.0000

Data Index: 7870 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6025. Min Act: 0.0000

Data Index: 1633590 (Python Code)

Max Activating Token Index: 233

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1139428 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6194. Min Act: -0.0000

Data Index: 427685 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1086623 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6084. Min Act: -0.0000

Data Index: 327749 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1069615 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1537505 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5758. Min Act: -0.0000

Data Index: 975922 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1265755 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1459986 (Python Code)

Max Activating Token Index: 898