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

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

Neuron 4656 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2440. Min Act: -0.0002

Data Index: 1639680 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2276. Min Act: -0.0002

Data Index: 1599939 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2273. Min Act: -0.0002

Data Index: 1559311 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2020. Min Act: -0.0002

Data Index: 1642011 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2039. Min Act: -0.0002

Data Index: 1496320 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2025. Min Act: -0.0002

Data Index: 1629034 (Python Code)

Max Activating Token Index: 589

Text #6

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1960. Min Act: -0.0002

Data Index: 1526488 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1851. Min Act: -0.0002

Data Index: 1541604 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1885. Min Act: -0.0002

Data Index: 1464495 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1852. Min Act: -0.0002

Data Index: 1644679 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1777. Min Act: -0.0002

Data Index: 1421512 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1834. Min Act: -0.0002

Data Index: 1397984 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1824. Min Act: -0.0002

Data Index: 1620374 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1753. Min Act: -0.0002

Data Index: 1602597 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1726. Min Act: -0.0002

Data Index: 1589467 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1426561 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1737. Min Act: -0.0002

Data Index: 1448877 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1754. Min Act: -0.0002

Data Index: 1643711 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1696. Min Act: -0.0002

Data Index: 1626889 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1697. Min Act: -0.0002

Data Index: 1398588 (Python Code)

Max Activating Token Index: 233