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

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

Neuron 1655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.5000. Min Act: -0.1700

Data Index: 127960 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.5000. Min Act: -0.1700

Data Index: 640741 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.4687. Min Act: -0.1700

Data Index: 54873 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.4062. Min Act: -0.1700

Data Index: 750059 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3750. Min Act: -0.1700

Data Index: 1054200 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3437. Min Act: -0.1700

Data Index: 88835 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3437. Min Act: -0.1700

Data Index: 481982 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3125. Min Act: -0.1700

Data Index: 894801 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3125. Min Act: -0.1700

Data Index: 247411 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 779770 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2812. Min Act: -0.1700

Data Index: 755887 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 850720 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 1344611 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2812. Min Act: -0.1700

Data Index: 785719 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 197433 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 64527 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 37906 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2812. Min Act: -0.1700

Data Index: 205082 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.1875. Min Act: -0.1700

Data Index: 441074 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.1875. Min Act: -0.1700

Data Index: 1140218 (C4 (Web Text))

Max Activating Token Index: 318