Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2030 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.5501. Min Act: -0.1700

Data Index: 1426953 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.4876. Min Act: -0.1700

Data Index: 1489070 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.4876. Min Act: -0.1700

Data Index: 1511385 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.4251. Min Act: -0.1700

Data Index: 1635771 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.4251. Min Act: -0.1700

Data Index: 1589892 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.4251. Min Act: -0.1700

Data Index: 1604473 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.4251. Min Act: -0.1700

Data Index: 1515580 (Python Code)

Max Activating Token Index: 484

Text #7

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1380648 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1444870 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1392525 (Python Code)

Max Activating Token Index: 868

Text #10

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1364234 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1592170 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1382212 (Python Code)

Max Activating Token Index: 694

Text #13

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3626. Min Act: -0.1700

Data Index: 1524137 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3001. Min Act: -0.1700

Data Index: 1396139 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3001. Min Act: -0.1700

Data Index: 1471965 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3001. Min Act: -0.1700

Data Index: 1488836 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3001. Min Act: -0.1700

Data Index: 1471559 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.3001. Min Act: -0.1700

Data Index: 1443552 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 5.5501. Min Range: -5.5501

Max Act: 5.2376. Min Act: -0.1700

Data Index: 1459616 (Python Code)

Max Activating Token Index: 556