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

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

Neuron 3980 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1502419 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 1.0252. Min Range: -1.0252

Max Act: 1.0252. Min Act: -0.0000

Data Index: 557720 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1257775 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.8556. Min Act: -0.0000

Data Index: 777752 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.8021. Min Act: -0.0000

Data Index: 934925 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1321758 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1466164 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1082366 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1599360 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1348525 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1276427 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1463520 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1290309 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7349. Min Act: -0.0000

Data Index: 385729 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1158510 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6950. Min Act: -0.0000

Data Index: 49965 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6668. Min Act: -0.0000

Data Index: 160277 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6714. Min Act: -0.0000

Data Index: 466693 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6914. Min Act: -0.0000

Data Index: 883220 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 1.0252. Min Range: -1.0252

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1203738 (C4 (Web Text))

Max Activating Token Index: 207