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

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

Neuron 1053 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: 5.0680. Min Range: -5.0680

Max Act: 5.0680. Min Act: -0.1700

Data Index: 1372149 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8180. Min Act: -0.1700

Data Index: 557926 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8180. Min Act: -0.1700

Data Index: 1470123 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8805. Min Act: -0.1700

Data Index: 1483446 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8180. Min Act: -0.1700

Data Index: 292908 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8492. Min Act: -0.1700

Data Index: 1563331 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8492. Min Act: -0.1700

Data Index: 1423600 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8492. Min Act: -0.1700

Data Index: 1649725 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8492. Min Act: -0.1700

Data Index: 1590931 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8492. Min Act: -0.1700

Data Index: 1021450 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7555. Min Act: -0.1700

Data Index: 924813 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.8492. Min Act: -0.1700

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7867. Min Act: -0.1700

Data Index: 1254536 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7867. Min Act: -0.1700

Data Index: 58612 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7867. Min Act: -0.1700

Data Index: 1427414 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7555. Min Act: -0.1700

Data Index: 1156295 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7555. Min Act: -0.1700

Data Index: 207916 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7242. Min Act: -0.1700

Data Index: 1391086 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.6930. Min Act: -0.1700

Data Index: 1539769 (Python Code)

Max Activating Token Index: 319

Text #19

Max Range: 5.0680. Min Range: -5.0680

Max Act: 4.7555. Min Act: -0.1700

Data Index: 1537592 (Python Code)

Max Activating Token Index: 673