Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1401956 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1610849 (Python Code)

Max Activating Token Index: 758

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1464774 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1465275 (Python Code)

Max Activating Token Index: 587

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1435164 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1504330 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1503530 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1418371 (Python Code)

Max Activating Token Index: 661

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1409164 (Python Code)

Max Activating Token Index: 524

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1374636 (Python Code)

Max Activating Token Index: 911

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1531703 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1494124 (Python Code)

Max Activating Token Index: 167

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1576010 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1434687 (Python Code)

Max Activating Token Index: 942

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1552404 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1511557 (Python Code)

Max Activating Token Index: 516

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1577136 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1564891 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1511765 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1436992 (Python Code)

Max Activating Token Index: 17