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

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

Neuron 713 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.2701. Min Act: -0.1700

Data Index: 1501711 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.2544. Min Act: -0.1700

Data Index: 1602223 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.2229. Min Act: -0.1700

Data Index: 1464008 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.1757. Min Act: -0.1700

Data Index: 1447517 (Python Code)

Max Activating Token Index: 818

Text #4

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.1600. Min Act: -0.1700

Data Index: 1535629 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1387834 (Python Code)

Max Activating Token Index: 404

Text #6

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.1127. Min Act: -0.1700

Data Index: 1381803 (Python Code)

Max Activating Token Index: 587

Text #7

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.0970. Min Act: -0.1700

Data Index: 1442302 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.0338. Min Act: -0.1700

Data Index: 1463701 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.0654. Min Act: -0.1700

Data Index: 1475721 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.0496. Min Act: -0.1700

Data Index: 882118 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.0338. Min Act: -0.1700

Data Index: 499837 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 3.2701. Min Range: -3.2701

Max Act: 3.0180. Min Act: -0.1700

Data Index: 1383748 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.9864. Min Act: -0.1700

Data Index: 1160435 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.9389. Min Act: -0.1700

Data Index: 834297 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.9389. Min Act: -0.1700

Data Index: 767535 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.9389. Min Act: -0.1700

Data Index: 1264284 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.9231. Min Act: -0.1700

Data Index: 846526 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.8914. Min Act: -0.1700

Data Index: 106531 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.2701. Min Range: -3.2701

Max Act: 2.8914. Min Act: -0.1700

Data Index: 843084 (C4 (Web Text))

Max Activating Token Index: 706