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

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

Neuron 4550 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: 0.6762. Min Range: -0.6762

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1421499 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1563531 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1482115 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1646348 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1656131 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1618152 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1370366 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1631286 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1502074 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1364129 (Python Code)

Max Activating Token Index: 65

Text #10

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1541602 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1494114 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1447674 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1364371 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1561910 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1565478 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1439270 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1467424 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1377407 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1622582 (Python Code)

Max Activating Token Index: 59