Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 409 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.1635. Min Act: -0.1700

Data Index: 1362250 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.1635. Min Act: -0.1700

Data Index: 1654379 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.1635. Min Act: -0.1700

Data Index: 1392257 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.0057. Min Act: -0.1700

Data Index: 1501795 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.0215. Min Act: -0.1700

Data Index: 1470332 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.0057. Min Act: -0.1700

Data Index: 1442428 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.1635. Min Range: -3.1635

Max Act: 3.0215. Min Act: -0.1700

Data Index: 1548678 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9741. Min Act: -0.1700

Data Index: 1371611 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9741. Min Act: -0.1700

Data Index: 1491946 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9899. Min Act: -0.1700

Data Index: 1543412 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9424. Min Act: -0.1700

Data Index: 1615541 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9266. Min Act: -0.1700

Data Index: 1477240 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9424. Min Act: -0.1700

Data Index: 1370576 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9108. Min Act: -0.1700

Data Index: 1553315 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.8949. Min Act: -0.1700

Data Index: 1470748 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.8949. Min Act: -0.1700

Data Index: 1552872 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.8949. Min Act: -0.1700

Data Index: 1413683 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9108. Min Act: -0.1700

Data Index: 1571915 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.9108. Min Act: -0.1700

Data Index: 1637084 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 3.1635. Min Range: -3.1635

Max Act: 2.8949. Min Act: -0.1700

Data Index: 1622670 (Python Code)

Max Activating Token Index: 2