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

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

Neuron 4714 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1567277 (Python Code)

Max Activating Token Index: 511

Text #1

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.0671. Min Act: 0.0001

Data Index: 1458105 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1504790 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8949. Min Act: 0.0000

Data Index: 1382322 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1593053 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9329. Min Act: 0.0002

Data Index: 1522593 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8776. Min Act: 0.0002

Data Index: 1450020 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8460. Min Act: 0.0000

Data Index: 1506058 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7905. Min Act: 0.0001

Data Index: 1466586 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1632132 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1484431 (Python Code)

Max Activating Token Index: 487

Text #11

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8089. Min Act: 0.0000

Data Index: 1532715 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1576994 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1606336 (Python Code)

Max Activating Token Index: 587

Text #14

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1629540 (Python Code)

Max Activating Token Index: 372

Text #15

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1505160 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7774. Min Act: 0.0002

Data Index: 1495548 (Python Code)

Max Activating Token Index: 448

Text #17

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7799. Min Act: 0.0001

Data Index: 1453616 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1514818 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1572105 (Python Code)

Max Activating Token Index: 519