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

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

Neuron 648 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: 3.3258. Min Range: -3.3258

Max Act: 3.3258. Min Act: -0.1700

Data Index: 820972 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1529. Min Act: -0.1700

Data Index: 846586 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1056. Min Act: -0.1700

Data Index: 206581 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1214. Min Act: -0.1700

Data Index: 874250 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0583. Min Act: -0.1700

Data Index: 973385 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0741. Min Act: -0.1700

Data Index: 417541 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0741. Min Act: -0.1700

Data Index: 1198738 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0583. Min Act: -0.1700

Data Index: 33875 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0583. Min Act: -0.1700

Data Index: 532974 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0109. Min Act: -0.1700

Data Index: 23913 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0267. Min Act: -0.1700

Data Index: 1229099 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0109. Min Act: -0.1700

Data Index: 530837 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9951. Min Act: -0.1700

Data Index: 738378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0425. Min Act: -0.1700

Data Index: 636644 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0109. Min Act: -0.1700

Data Index: 699625 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9793. Min Act: -0.1700

Data Index: 124375 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.0267. Min Act: -0.1700

Data Index: 238803 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9951. Min Act: -0.1700

Data Index: 671108 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9951. Min Act: -0.1700

Data Index: 350826 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 3.3258. Min Range: -3.3258

Max Act: 2.9951. Min Act: -0.1700

Data Index: 217355 (C4 (Web Text))

Max Activating Token Index: 460