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

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

Neuron 1992 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: 3.7394. Min Range: -3.7394

Max Act: 3.7081. Min Act: -0.1700

Data Index: 797533 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.7394. Min Act: -0.1700

Data Index: 1332615 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6768. Min Act: -0.1700

Data Index: 1281462 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.7081. Min Act: -0.1700

Data Index: 580772 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6768. Min Act: -0.1700

Data Index: 21523 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6768. Min Act: -0.1700

Data Index: 673942 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6455. Min Act: -0.1700

Data Index: 703933 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6455. Min Act: -0.1700

Data Index: 845237 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6142. Min Act: -0.1700

Data Index: 126975 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6142. Min Act: -0.1700

Data Index: 727141 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6142. Min Act: -0.1700

Data Index: 1097285 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6142. Min Act: -0.1700

Data Index: 1230781 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.6142. Min Act: -0.1700

Data Index: 895885 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 290791 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 935927 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 961555 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 250991 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 892544 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 5457 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 3.7394. Min Range: -3.7394

Max Act: 3.5828. Min Act: -0.1700

Data Index: 586518 (C4 (Web Text))

Max Activating Token Index: 244