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

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

Neuron 1665 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: 3.4859. Min Range: -3.4859

Max Act: 3.4859. Min Act: -0.1700

Data Index: 1613636 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1576425 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4389. Min Act: -0.1700

Data Index: 1365390 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4389. Min Act: -0.1700

Data Index: 1441561 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4389. Min Act: -0.1700

Data Index: 1606949 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1413298 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4389. Min Act: -0.1700

Data Index: 1543773 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4389. Min Act: -0.1700

Data Index: 1495026 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4232. Min Act: -0.1700

Data Index: 1600982 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4075. Min Act: -0.1700

Data Index: 1438892 (Python Code)

Max Activating Token Index: 901

Text #10

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4075. Min Act: -0.1700

Data Index: 1639839 (Python Code)

Max Activating Token Index: 262

Text #11

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4232. Min Act: -0.1700

Data Index: 1400476 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4232. Min Act: -0.1700

Data Index: 1408195 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4232. Min Act: -0.1700

Data Index: 1548871 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3918. Min Act: -0.1700

Data Index: 1552724 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3918. Min Act: -0.1700

Data Index: 1629531 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4075. Min Act: -0.1700

Data Index: 1618377 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3918. Min Act: -0.1700

Data Index: 1608261 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4075. Min Act: -0.1700

Data Index: 1393102 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3918. Min Act: -0.1700

Data Index: 1378082 (Python Code)

Max Activating Token Index: 40