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

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

Neuron 4261 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5624. Min Act: -0.0001

Data Index: 1567862 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5289. Min Act: -0.0002

Data Index: 1455140 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1616550 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4949. Min Act: -0.0002

Data Index: 1368752 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4857. Min Act: -0.0001

Data Index: 1603178 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1400483 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1626527 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4805. Min Act: -0.0001

Data Index: 1444530 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4809. Min Act: -0.0001

Data Index: 1581804 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1592230 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4761. Min Act: -0.0001

Data Index: 1446959 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1652993 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4744. Min Act: -0.0001

Data Index: 1482847 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4761. Min Act: -0.0002

Data Index: 1431748 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4653. Min Act: -0.0001

Data Index: 1428689 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4712. Min Act: -0.0002

Data Index: 1621045 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4637. Min Act: -0.0001

Data Index: 1496685 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1409405 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4619. Min Act: -0.0002

Data Index: 1435579 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4711. Min Act: -0.0001

Data Index: 1638281 (Python Code)

Max Activating Token Index: 15