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

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

Neuron 3028 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1499926 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1431954 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1493762 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1459962 (Python Code)

Max Activating Token Index: 206

Text #4

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1456351 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1398341 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1481659 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1599960 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1437978 (Python Code)

Max Activating Token Index: 182

Text #9

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1652257 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1578602 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1607516 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1653963 (Python Code)

Max Activating Token Index: 558

Text #13

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1442145 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1417055 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1467085 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1386186 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1417136 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1573563 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.7686. Min Range: -0.7686

Max Act: 0.5000. Min Act: 0.0000

Data Index: 1645870 (Python Code)

Max Activating Token Index: 941