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

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

Neuron 532 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: 3.1687. Min Range: -3.1687

Max Act: 3.1687. Min Act: -0.1700

Data Index: 187242 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.1529. Min Act: -0.1700

Data Index: 332946 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.1687. Min Act: -0.1700

Data Index: 397740 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.1056. Min Act: -0.1700

Data Index: 385178 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0899. Min Act: -0.1700

Data Index: 380096 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0899. Min Act: -0.1700

Data Index: 343696 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0425. Min Act: -0.1700

Data Index: 455928 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0741. Min Act: -0.1700

Data Index: 561023 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0899. Min Act: -0.1700

Data Index: 1296863 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0425. Min Act: -0.1700

Data Index: 38547 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 3.1687. Min Range: -3.1687

Max Act: 2.9951. Min Act: -0.1700

Data Index: 440965 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0267. Min Act: -0.1700

Data Index: 327976 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0425. Min Act: -0.1700

Data Index: 364112 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0425. Min Act: -0.1700

Data Index: 1216513 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0425. Min Act: -0.1700

Data Index: 252867 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0425. Min Act: -0.1700

Data Index: 1155969 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0267. Min Act: -0.1700

Data Index: 272656 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 3.1687. Min Range: -3.1687

Max Act: 3.0267. Min Act: -0.1700

Data Index: 453693 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 3.1687. Min Range: -3.1687

Max Act: 2.9951. Min Act: -0.1700

Data Index: 10527 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.1687. Min Range: -3.1687

Max Act: 2.9951. Min Act: -0.1700

Data Index: 896244 (C4 (Web Text))

Max Activating Token Index: 574