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

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

Neuron 1137 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1434216 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.1808. Min Act: -0.1700

Data Index: 1623407 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.1335. Min Act: -0.1700

Data Index: 1634837 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.1020. Min Act: -0.1700

Data Index: 1482625 (Python Code)

Max Activating Token Index: 588

Text #4

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.1335. Min Act: -0.1700

Data Index: 1609118 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0705. Min Act: -0.1700

Data Index: 1152381 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0862. Min Act: -0.1700

Data Index: 1498722 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0547. Min Act: -0.1700

Data Index: 1382042 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0705. Min Act: -0.1700

Data Index: 1586527 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0547. Min Act: -0.1700

Data Index: 1506718 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0389. Min Act: -0.1700

Data Index: 478004 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0389. Min Act: -0.1700

Data Index: 1439631 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0389. Min Act: -0.1700

Data Index: 1376285 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0231. Min Act: -0.1700

Data Index: 1631462 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0073. Min Act: -0.1700

Data Index: 1400152 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.9915. Min Act: -0.1700

Data Index: 1558752 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0073. Min Act: -0.1700

Data Index: 1462893 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0073. Min Act: -0.1700

Data Index: 1494399 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 3.2122. Min Range: -3.2122

Max Act: 3.0073. Min Act: -0.1700

Data Index: 1399782 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 3.2122. Min Range: -3.2122

Max Act: 2.9915. Min Act: -0.1700

Data Index: 863484 (C4 (Web Text))

Max Activating Token Index: 752