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

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

Neuron 3400 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4838. Min Act: -0.0001

Data Index: 73334 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4114. Min Act: -0.0001

Data Index: 1403781 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3756. Min Act: -0.0001

Data Index: 1601046 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1512577 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1466988 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1423307 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1619947 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1595017 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3634. Min Act: -0.0001

Data Index: 1347290 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1634071 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1454260 (Python Code)

Max Activating Token Index: 510

Text #11

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1449417 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3834. Min Act: -0.0001

Data Index: 721843 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1506160 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1631037 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1598525 (Python Code)

Max Activating Token Index: 686

Text #16

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1584548 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1622561 (Python Code)

Max Activating Token Index: 622

Text #18

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1631328 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1531030 (Python Code)

Max Activating Token Index: 918