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

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

Neuron 1302 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.8799. Min Act: -0.1700

Data Index: 1400017 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1519379 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1652728 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.8173. Min Act: -0.1700

Data Index: 1446060 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1583870 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1571337 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1570890 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1564602 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1543495 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1593133 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1392924 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1635471 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1389017 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1496430 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1625308 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1640740 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7548. Min Act: -0.1700

Data Index: 1558947 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7548. Min Act: -0.1700

Data Index: 1492988 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7235. Min Act: -0.1700

Data Index: 1443464 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7548. Min Act: -0.1700

Data Index: 1601965 (Python Code)

Max Activating Token Index: 28