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

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

Neuron 623 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: 0.9636. Min Range: -0.9636

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1650331 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1464999 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1313931 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1584883 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9266. Min Act: -0.0001

Data Index: 847905 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1643812 (Python Code)

Max Activating Token Index: 224

Text #6

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8346. Min Act: -0.0000

Data Index: 970670 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9146. Min Act: -0.0000

Data Index: 255327 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1476697 (Python Code)

Max Activating Token Index: 389

Text #9

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1496456 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9209. Min Act: -0.0000

Data Index: 954595 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1476768 (Python Code)

Max Activating Token Index: 545

Text #12

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1586610 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1589427 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1370953 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1580424 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8495. Min Act: -0.0000

Data Index: 905392 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1376897 (Python Code)

Max Activating Token Index: 487

Text #18

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1529480 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1524992 (Python Code)

Max Activating Token Index: 685