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

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

Neuron 3411 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: 0.2058. Min Range: -0.2058

Max Act: 0.2058. Min Act: -0.0002

Data Index: 1374830 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1951. Min Act: -0.0002

Data Index: 1448474 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1837. Min Act: -0.0002

Data Index: 1605094 (Python Code)

Max Activating Token Index: 337

Text #3

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1818. Min Act: -0.0002

Data Index: 1519809 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1765. Min Act: -0.0002

Data Index: 1555962 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1685. Min Act: -0.0002

Data Index: 1530240 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1478501 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1714. Min Act: -0.0002

Data Index: 1524813 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1757. Min Act: -0.0002

Data Index: 1415477 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1677. Min Act: -0.0002

Data Index: 1645401 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1601. Min Act: -0.0002

Data Index: 1528642 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1584. Min Act: -0.0002

Data Index: 1448503 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1608. Min Act: -0.0002

Data Index: 1420958 (Python Code)

Max Activating Token Index: 569

Text #13

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1634. Min Act: -0.0002

Data Index: 1500037 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1553. Min Act: -0.0002

Data Index: 1651234 (Python Code)

Max Activating Token Index: 578

Text #15

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1659. Min Act: -0.0002

Data Index: 1549465 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1591. Min Act: -0.0002

Data Index: 1417019 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1432589 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1542. Min Act: -0.0002

Data Index: 1503930 (Python Code)

Max Activating Token Index: 498

Text #19

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1485545 (Python Code)

Max Activating Token Index: 458