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

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

Neuron 118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.7880. Min Act: -0.1700

Data Index: 1543200 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.7880. Min Act: -0.1700

Data Index: 1575743 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.7098. Min Act: -0.1700

Data Index: 1444746 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6785. Min Act: -0.1700

Data Index: 1460399 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6941. Min Act: -0.1700

Data Index: 1413142 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1561818 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6628. Min Act: -0.1700

Data Index: 1565343 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6472. Min Act: -0.1700

Data Index: 1528067 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6159. Min Act: -0.1700

Data Index: 1473998 (Python Code)

Max Activating Token Index: 949

Text #9

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6159. Min Act: -0.1700

Data Index: 1453483 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6002. Min Act: -0.1700

Data Index: 1362931 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6159. Min Act: -0.1700

Data Index: 1548954 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1386759 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6002. Min Act: -0.1700

Data Index: 1513589 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6002. Min Act: -0.1700

Data Index: 1609942 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6628. Min Act: -0.1700

Data Index: 1624897 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6002. Min Act: -0.1700

Data Index: 1624948 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5532. Min Act: -0.1700

Data Index: 1560986 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1613175 (Python Code)

Max Activating Token Index: 857

Text #19

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1545737 (Python Code)

Max Activating Token Index: 978