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

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

Neuron 4514 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.5958. Min Act: -0.0000

Data Index: 1631822 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.2095. Min Act: -0.0000

Data Index: 1615420 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.2384. Min Act: -0.0000

Data Index: 1545405 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9438. Min Act: -0.0000

Data Index: 1397417 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.1433. Min Act: -0.0000

Data Index: 1627210 (Python Code)

Max Activating Token Index: 396

Text #5

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.1104. Min Act: -0.0000

Data Index: 1590303 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.0153. Min Act: -0.0000

Data Index: 1486378 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9021. Min Act: -0.0000

Data Index: 1398270 (Python Code)

Max Activating Token Index: 629

Text #8

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1381480 (Python Code)

Max Activating Token Index: 235

Text #9

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9917. Min Act: -0.0000

Data Index: 1583416 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9787. Min Act: -0.0000

Data Index: 1628132 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.8464. Min Act: -0.0000

Data Index: 1621063 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 2.5958. Min Range: -2.5958

Max Act: 2.0600. Min Act: -0.0000

Data Index: 1618863 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9122. Min Act: -0.0000

Data Index: 1464556 (Python Code)

Max Activating Token Index: 432

Text #14

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1395408 (Python Code)

Max Activating Token Index: 795

Text #15

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.9842. Min Act: -0.0000

Data Index: 1360394 (Python Code)

Max Activating Token Index: 612

Text #16

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1579701 (Python Code)

Max Activating Token Index: 914

Text #17

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1544532 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.8035. Min Act: -0.0000

Data Index: 1517161 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 2.5958. Min Range: -2.5958

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1474522 (Python Code)

Max Activating Token Index: 858