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

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

Neuron 493 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.8000. Min Act: -0.1700

Data Index: 166341 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.5500. Min Act: -0.1700

Data Index: 1240861 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.5500. Min Act: -0.1700

Data Index: 169184 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.3937. Min Act: -0.1700

Data Index: 312546 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.3625. Min Act: -0.1700

Data Index: 379844 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.3625. Min Act: -0.1700

Data Index: 1357665 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2999. Min Act: -0.1700

Data Index: 1022121 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 631797 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2999. Min Act: -0.1700

Data Index: 1016739 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2999. Min Act: -0.1700

Data Index: 1221897 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 1061542 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 1095243 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 798892 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.1124. Min Act: -0.1700

Data Index: 416718 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2062. Min Act: -0.1700

Data Index: 273647 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 765360 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 392835 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.1749. Min Act: -0.1700

Data Index: 143492 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.1749. Min Act: -0.1700

Data Index: 771506 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 4.8000. Min Range: -4.8000

Max Act: 4.2374. Min Act: -0.1700

Data Index: 70322 (C4 (Web Text))

Max Activating Token Index: 841