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

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

Neuron 3807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1529345 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1591420 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1527702 (Python Code)

Max Activating Token Index: 614

Text #3

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1586911 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1369663 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1427409 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1441968 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1634010 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1465482 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1424636 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1604238 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1368117 (Python Code)

Max Activating Token Index: 198

Text #12

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1517803 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1543836 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1437760 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1394676 (Python Code)

Max Activating Token Index: 860

Text #16

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1550312 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1416485 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1494171 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1560961 (Python Code)

Max Activating Token Index: 78