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

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

Neuron 418 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1248900 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0859. Min Act: -0.0001

Data Index: 622324 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0802. Min Act: -0.0001

Data Index: 376946 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1269848 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1520759 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0691. Min Act: -0.0001

Data Index: 929484 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0694. Min Act: -0.0001

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1333298 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0610. Min Act: -0.0001

Data Index: 154231 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0673. Min Act: -0.0001

Data Index: 233660 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1621349 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1032235 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0738. Min Act: -0.0001

Data Index: 299577 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0612. Min Act: -0.0001

Data Index: 811965 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0626. Min Act: -0.0001

Data Index: 861828 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0585. Min Act: -0.0001

Data Index: 950514 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1064986 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0581. Min Act: -0.0001

Data Index: 487554 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0610. Min Act: -0.0001

Data Index: 896608 (C4 (Web Text))

Max Activating Token Index: 718