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

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

Neuron 2209 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.6899. Min Act: -0.0000

Data Index: 1514951 (Python Code)

Max Activating Token Index: 555

Text #1

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1394278 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1485769 (Python Code)

Max Activating Token Index: 509

Text #3

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1471593 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1584164 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.5920. Min Act: -0.0000

Data Index: 1577401 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1474375 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.4583. Min Act: -0.0000

Data Index: 1526386 (Python Code)

Max Activating Token Index: 792

Text #8

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1499784 (Python Code)

Max Activating Token Index: 965

Text #9

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1385371 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1456903 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1406470 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1375619 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1513684 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1405673 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1368751 (Python Code)

Max Activating Token Index: 865

Text #16

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1579464 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1578065 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1576930 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 1.6899. Min Range: -1.6899

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1526011 (Python Code)

Max Activating Token Index: 957