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

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

Neuron 3750 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0252. Min Range: -2.0252

Max Act: 2.0252. Min Act: -0.0000

Data Index: 440341 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.8902. Min Act: -0.0000

Data Index: 812466 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.9730. Min Act: -0.0000

Data Index: 88280 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.8271. Min Act: -0.0000

Data Index: 821663 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.8295. Min Act: -0.0000

Data Index: 138544 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.8025. Min Act: -0.0000

Data Index: 977355 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.7068. Min Act: -0.0001

Data Index: 1204745 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.7591. Min Act: -0.0000

Data Index: 192389 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.7215. Min Act: -0.0000

Data Index: 654427 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6886. Min Act: -0.0000

Data Index: 959788 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6836. Min Act: -0.0000

Data Index: 854500 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6736. Min Act: -0.0000

Data Index: 509013 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6644. Min Act: 0.0000

Data Index: 134348 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6363. Min Act: 0.0000

Data Index: 1164251 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.5382. Min Act: -0.0000

Data Index: 362274 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6442. Min Act: -0.0000

Data Index: 622515 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1117495 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.5364. Min Act: -0.0000

Data Index: 1102035 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.5721. Min Act: -0.0001

Data Index: 233346 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 2.0252. Min Range: -2.0252

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1287981 (C4 (Web Text))

Max Activating Token Index: 32