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

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

Neuron 4556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1401043 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1642311 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1510255 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1457181 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1568830 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1565612 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1447869 (Python Code)

Max Activating Token Index: 24

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1573740 (Python Code)

Max Activating Token Index: 395

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1443153 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1458497 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1469179 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0480. Min Act: -0.0002

Data Index: 472666 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1502104 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1477648 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1551025 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1420262 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1510192 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1525093 (Python Code)

Max Activating Token Index: 711

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0425. Min Act: -0.0002

Data Index: 961151 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1627234 (Python Code)

Max Activating Token Index: 302