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

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

Neuron 5155 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: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0001

Data Index: 1636079 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1521421 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8103. Min Act: -0.0002

Data Index: 1472995 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8017. Min Act: -0.0001

Data Index: 1374585 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8089. Min Act: -0.0001

Data Index: 1626667 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7890. Min Act: -0.0002

Data Index: 1393895 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7980. Min Act: -0.0001

Data Index: 1548960 (Python Code)

Max Activating Token Index: 760

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7813. Min Act: -0.0002

Data Index: 1592584 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1564242 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7989. Min Act: -0.0001

Data Index: 1471810 (Python Code)

Max Activating Token Index: 414

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7839. Min Act: -0.0001

Data Index: 1430503 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1626440 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7855. Min Act: -0.0001

Data Index: 1361671 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7833. Min Act: -0.0002

Data Index: 1575557 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7708. Min Act: -0.0001

Data Index: 1505643 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7623. Min Act: -0.0001

Data Index: 1614271 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7710. Min Act: -0.0001

Data Index: 1420564 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7641. Min Act: -0.0001

Data Index: 1572531 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7605. Min Act: -0.0001

Data Index: 1553374 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1595739 (Python Code)

Max Activating Token Index: 103