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

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

Neuron 3350 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: 2.8813. Min Range: -2.8813

Max Act: 2.8813. Min Act: -0.0000

Data Index: 1353833 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 2.8813. Min Range: -2.8813

Max Act: 2.2086. Min Act: -0.0000

Data Index: 553086 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 2.8813. Min Range: -2.8813

Max Act: 2.0446. Min Act: -0.0000

Data Index: 1110585 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.9579. Min Act: -0.0000

Data Index: 1256033 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 2.8813. Min Range: -2.8813

Max Act: 2.0547. Min Act: 0.0000

Data Index: 209318 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.9485. Min Act: -0.0000

Data Index: 580950 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.8353. Min Act: -0.0000

Data Index: 1086238 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.6890. Min Act: -0.0000

Data Index: 1065500 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.8880. Min Act: -0.0000

Data Index: 480743 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.7185. Min Act: -0.0000

Data Index: 536323 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.6913. Min Act: -0.0000

Data Index: 805926 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.6955. Min Act: -0.0000

Data Index: 276533 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.5393. Min Act: 0.0000

Data Index: 1162283 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.5103. Min Act: -0.0000

Data Index: 333119 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.5051. Min Act: -0.0000

Data Index: 474258 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.4744. Min Act: -0.0000

Data Index: 319925 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.5790. Min Act: -0.0000

Data Index: 778854 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.5266. Min Act: -0.0000

Data Index: 1633008 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.4974. Min Act: -0.0000

Data Index: 6822 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 2.8813. Min Range: -2.8813

Max Act: 1.5638. Min Act: -0.0000

Data Index: 610870 (C4 (Web Text))

Max Activating Token Index: 390