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

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

Neuron 1746 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1441847 (Python Code)

Max Activating Token Index: 692

Text #1

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1584104 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1420248 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1511519 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1651735 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1365953 (Python Code)

Max Activating Token Index: 396

Text #6

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1495558 (Python Code)

Max Activating Token Index: 509

Text #7

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1375070 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1368132 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1390486 (Python Code)

Max Activating Token Index: 436

Text #10

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1495160 (Python Code)

Max Activating Token Index: 298

Text #11

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1654505 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1460899 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1432050 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1495705 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1612464 (Python Code)

Max Activating Token Index: 754

Text #16

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4051. Min Act: -0.0000

Data Index: 312702 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1429280 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1481066 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1598766 (Python Code)

Max Activating Token Index: 427