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

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

Neuron 5603 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: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1584693 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1579938 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1541134 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1413840 (Python Code)

Max Activating Token Index: 662

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1541347 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1397374 (Python Code)

Max Activating Token Index: 958

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1601473 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1471772 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1414053 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1540535 (Python Code)

Max Activating Token Index: 472

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1610714 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1629460 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1466876 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1620303 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1544775 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1421521 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1592947 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1512068 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1619653 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1576274 (Python Code)

Max Activating Token Index: 527