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

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

Neuron 321 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1410767 (Python Code)

Max Activating Token Index: 247

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1549918 (Python Code)

Max Activating Token Index: 127

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1616119 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1599040 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1502778 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1617954 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1566462 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1517049 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1533129 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1636722 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1449679 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1545145 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1607898 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1634868 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1513358 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1637909 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1381082 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1500579 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1557123 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1453216 (Python Code)

Max Activating Token Index: 200