Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 766 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 6.1038. Min Range: -6.1038

Max Act: 6.1038. Min Act: -0.1700

Data Index: 1588609 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.7913. Min Act: -0.1700

Data Index: 1496482 (Python Code)

Max Activating Token Index: 443

Text #2

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.8538. Min Act: -0.1700

Data Index: 1648500 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.8538. Min Act: -0.1700

Data Index: 1491870 (Python Code)

Max Activating Token Index: 113

Text #4

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.6975. Min Act: -0.1700

Data Index: 1569877 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.6663. Min Act: -0.1700

Data Index: 1584859 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.6663. Min Act: -0.1700

Data Index: 1598420 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5725. Min Act: -0.1700

Data Index: 1436037 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.6663. Min Act: -0.1700

Data Index: 1415352 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.6038. Min Act: -0.1700

Data Index: 1373301 (Python Code)

Max Activating Token Index: 305

Text #10

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5413. Min Act: -0.1700

Data Index: 1466690 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5725. Min Act: -0.1700

Data Index: 1385005 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5100. Min Act: -0.1700

Data Index: 1444534 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5413. Min Act: -0.1700

Data Index: 1400196 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.4788. Min Act: -0.1700

Data Index: 1444857 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5413. Min Act: -0.1700

Data Index: 1391702 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5413. Min Act: -0.1700

Data Index: 1440240 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5100. Min Act: -0.1700

Data Index: 1637939 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.5100. Min Act: -0.1700

Data Index: 1426401 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 6.1038. Min Range: -6.1038

Max Act: 5.4788. Min Act: -0.1700

Data Index: 1597474 (Python Code)

Max Activating Token Index: 615