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

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

Neuron 21 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: 0.0743. Min Range: -0.0743

Max Act: 0.0726. Min Act: -0.0001

Data Index: 827628 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1532922 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1373340 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1175913 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1427020 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1540401 (Python Code)

Max Activating Token Index: 911

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1388905 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1605964 (Python Code)

Max Activating Token Index: 471

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1390374 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1438735 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1384684 (Python Code)

Max Activating Token Index: 521

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1513053 (Python Code)

Max Activating Token Index: 704

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1588525 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1571966 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1620628 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1614885 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1414822 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1397516 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1607829 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1524981 (Python Code)

Max Activating Token Index: 425