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

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

Neuron 4270 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7871. Min Range: -3.7871

Max Act: 3.7871. Min Act: -0.0000

Data Index: 1561154 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.8573. Min Act: -0.0000

Data Index: 1462376 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.6645. Min Act: -0.0000

Data Index: 1555215 (Python Code)

Max Activating Token Index: 608

Text #3

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.7102. Min Act: -0.0000

Data Index: 1534395 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.5678. Min Act: -0.0000

Data Index: 1601425 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.3731. Min Act: -0.0000

Data Index: 1616676 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1615692 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1585668 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.5445. Min Act: -0.0000

Data Index: 1426125 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.3829. Min Act: -0.0000

Data Index: 1410489 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.3346. Min Act: -0.0000

Data Index: 1464612 (Python Code)

Max Activating Token Index: 257

Text #11

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.3308. Min Act: -0.0000

Data Index: 1602275 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.3307. Min Act: -0.0000

Data Index: 1556641 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.2915. Min Act: -0.0000

Data Index: 1601813 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1494808 (Python Code)

Max Activating Token Index: 239

Text #15

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.0880. Min Act: -0.0000

Data Index: 1607508 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.1905. Min Act: -0.0000

Data Index: 1524367 (Python Code)

Max Activating Token Index: 547

Text #17

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1640774 (Python Code)

Max Activating Token Index: 412

Text #18

Max Range: 3.7871. Min Range: -3.7871

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1549128 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 3.7871. Min Range: -3.7871

Max Act: 2.0909. Min Act: -0.0000

Data Index: 1578156 (Python Code)

Max Activating Token Index: 408