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

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

Neuron 1411 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.2344. Min Act: -0.0002

Data Index: 1653954 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.2093. Min Act: -0.0002

Data Index: 1481469 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1912. Min Act: -0.0002

Data Index: 1441620 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1798. Min Act: -0.0002

Data Index: 1589926 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1779. Min Act: -0.0002

Data Index: 1430476 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1762. Min Act: -0.0002

Data Index: 1597152 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1784. Min Act: -0.0002

Data Index: 1380410 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1439893 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1765. Min Act: -0.0002

Data Index: 1594521 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1768. Min Act: -0.0002

Data Index: 1479971 (Python Code)

Max Activating Token Index: 840

Text #10

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1767. Min Act: -0.0002

Data Index: 1495753 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1433440 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1710. Min Act: -0.0002

Data Index: 1529989 (Python Code)

Max Activating Token Index: 470

Text #13

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1749. Min Act: -0.0002

Data Index: 1546039 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1450218 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1738. Min Act: -0.0002

Data Index: 1368218 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1711. Min Act: -0.0002

Data Index: 1650971 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1667. Min Act: -0.0002

Data Index: 1509055 (Python Code)

Max Activating Token Index: 734

Text #18

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1648. Min Act: -0.0002

Data Index: 1438930 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.2344. Min Range: -0.2344

Max Act: 0.1679. Min Act: -0.0002

Data Index: 1577586 (Python Code)

Max Activating Token Index: 455