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

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

Neuron 3540 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1569101 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0778. Min Act: -0.0001

Data Index: 83295 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1080059 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1454497 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1541362 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1642384 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1505365 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1354387 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1471213 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1499520 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1648584 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1003615 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1197413 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1433675 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1640704 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1158947 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1538306 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1451475 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1634555 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1431623 (Python Code)

Max Activating Token Index: 605