Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1654004 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1533869 (Python Code)

Max Activating Token Index: 468

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1405448 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1650121 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1556592 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1651256 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1431443 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1393056 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1448064 (Python Code)

Max Activating Token Index: 407

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1415932 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1588566 (Python Code)

Max Activating Token Index: 596

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1480487 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1631433 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1406516 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1537468 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1558114 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1443097 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1439127 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1464359 (Python Code)

Max Activating Token Index: 881

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1559980 (Python Code)

Max Activating Token Index: 612