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

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

Neuron 1572 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1451544 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1431892 (Python Code)

Max Activating Token Index: 1011

Text #2

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1565644 (Python Code)

Max Activating Token Index: 868

Text #3

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1530633 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1395322 (Python Code)

Max Activating Token Index: 589

Text #5

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1479880 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7163. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1464073 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1557232 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1389970 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1408307 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1391980 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6138. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1571556 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1377002 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1471061 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1395669 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5005. Min Act: -0.0000

Data Index: 340795 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1427615 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1453370 (Python Code)

Max Activating Token Index: 456