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

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

Neuron 539 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.9716. Min Act: -0.0000

Data Index: 1576704 (Python Code)

Max Activating Token Index: 538

Text #1

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1568611 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1486131 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1450267 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1608876 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1407737 (Python Code)

Max Activating Token Index: 630

Text #6

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1448152 (Python Code)

Max Activating Token Index: 497

Text #7

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1648555 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1375751 (Python Code)

Max Activating Token Index: 944

Text #9

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1572692 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1361935 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1650814 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1469286 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1573569 (Python Code)

Max Activating Token Index: 836

Text #14

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1448972 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1492696 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1406750 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1484379 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.0175. Min Act: -0.0000

Data Index: 1600715 (Python Code)

Max Activating Token Index: 438

Text #19

Max Range: 1.9716. Min Range: -1.9716

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1650129 (Python Code)

Max Activating Token Index: 541