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

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

Neuron 4407 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0704. Min Range: -1.0704

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1507692 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1620055 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1571737 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 1.0704. Min Range: -1.0704

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1408136 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1473522 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1372506 (Python Code)

Max Activating Token Index: 898

Text #6

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1411561 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1507142 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1457780 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1599477 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1616973 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1433891 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1437363 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1373246 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1595270 (Python Code)

Max Activating Token Index: 46

Text #15

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1555745 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1453307 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1543877 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1597080 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1613070 (Python Code)

Max Activating Token Index: 87