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

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

Neuron 1328 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: 3.0834. Min Range: -3.0834

Max Act: 3.0834. Min Act: -0.1700

Data Index: 1564935 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8619. Min Act: -0.1700

Data Index: 51601 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8777. Min Act: -0.1700

Data Index: 1509681 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8301. Min Act: -0.1700

Data Index: 1289107 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8460. Min Act: -0.1700

Data Index: 1643249 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8142. Min Act: -0.1700

Data Index: 1534514 (Python Code)

Max Activating Token Index: 923

Text #6

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7504. Min Act: -0.1700

Data Index: 1460086 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7504. Min Act: -0.1700

Data Index: 1448152 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7823. Min Act: -0.1700

Data Index: 1610452 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7344. Min Act: -0.1700

Data Index: 1470706 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7504. Min Act: -0.1700

Data Index: 1533801 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7184. Min Act: -0.1700

Data Index: 808574 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7344. Min Act: -0.1700

Data Index: 1258765 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7344. Min Act: -0.1700

Data Index: 1373953 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7504. Min Act: -0.1700

Data Index: 1618339 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7504. Min Act: -0.1700

Data Index: 1537023 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7344. Min Act: -0.1700

Data Index: 1423671 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.6704. Min Act: -0.1700

Data Index: 1597372 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7025. Min Act: -0.1700

Data Index: 689917 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.6544. Min Act: -0.1700

Data Index: 1573024 (Python Code)

Max Activating Token Index: 1023