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

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

Neuron 1885 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1419319 (Python Code)

Max Activating Token Index: 377

Text #1

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1526628 (Python Code)

Max Activating Token Index: 888

Text #2

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1447463 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1445566 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1600459 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1360258 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1551510 (Python Code)

Max Activating Token Index: 851

Text #7

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1579520 (Python Code)

Max Activating Token Index: 756

Text #8

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1518060 (Python Code)

Max Activating Token Index: 67

Text #9

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1423405 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1572904 (Python Code)

Max Activating Token Index: 924

Text #11

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1551097 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1562776 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1516867 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1649867 (Python Code)

Max Activating Token Index: 321

Text #15

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1469882 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1487572 (Python Code)

Max Activating Token Index: 50

Text #17

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1635676 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1565945 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 1.5829. Min Range: -1.5829

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1440804 (Python Code)

Max Activating Token Index: 190