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

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

Neuron 3173 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1411087 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1509775 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1383669 (Python Code)

Max Activating Token Index: 455

Text #3

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1538372 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1438846 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1636365 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1563348 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1436442 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1577735 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1078422 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1575124 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1508169 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1416420 (Python Code)

Max Activating Token Index: 125

Text #13

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1430820 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1430678 (Python Code)

Max Activating Token Index: 800

Text #15

Max Range: 1.5220. Min Range: -1.5220

Max Act: 0.9863. Min Act: -0.0000

Data Index: 504971 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0450. Min Act: -0.0000

Data Index: 637371 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.5220. Min Range: -1.5220

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1548748 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.5220. Min Range: -1.5220

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1581938 (Python Code)

Max Activating Token Index: 739

Text #19

Max Range: 1.5220. Min Range: -1.5220

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1616340 (Python Code)

Max Activating Token Index: 835