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

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

Neuron 1567 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.5537. Min Act: 0.0000

Data Index: 1443944 (Python Code)

Max Activating Token Index: 337

Text #1

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4465. Min Act: 0.0001

Data Index: 1475746 (Python Code)

Max Activating Token Index: 217

Text #2

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4534. Min Act: 0.0000

Data Index: 1395967 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4361. Min Act: 0.0000

Data Index: 1502491 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1532100 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1392741 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1396890 (Python Code)

Max Activating Token Index: 423

Text #7

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3816. Min Act: 0.0000

Data Index: 1461351 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3652. Min Act: 0.0000

Data Index: 1369920 (Python Code)

Max Activating Token Index: 197

Text #9

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3776. Min Act: 0.0000

Data Index: 1633348 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3901. Min Act: 0.0000

Data Index: 1548641 (Python Code)

Max Activating Token Index: 430

Text #11

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1415854 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3790. Min Act: 0.0000

Data Index: 1520241 (Python Code)

Max Activating Token Index: 543

Text #13

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3828. Min Act: 0.0000

Data Index: 1567673 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1370461 (Python Code)

Max Activating Token Index: 392

Text #15

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1551800 (Python Code)

Max Activating Token Index: 238

Text #16

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1481747 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1553789 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1520735 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 0.5537. Min Range: -0.5537

Max Act: 0.3474. Min Act: 0.0000

Data Index: 1410665 (Python Code)

Max Activating Token Index: 616