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

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

Neuron 577 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: 3.0928. Min Range: -3.0928

Max Act: 3.0770. Min Act: -0.1700

Data Index: 7295 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0928. Min Act: -0.1700

Data Index: 1260508 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0928. Min Act: -0.1700

Data Index: 1294827 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0928. Min Act: -0.1700

Data Index: 144621 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0770. Min Act: -0.1700

Data Index: 57595 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0455. Min Act: -0.1700

Data Index: 292689 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0770. Min Act: -0.1700

Data Index: 878589 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0612. Min Act: -0.1700

Data Index: 487554 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0139. Min Act: -0.1700

Data Index: 556508 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0139. Min Act: -0.1700

Data Index: 1352145 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0612. Min Act: -0.1700

Data Index: 870260 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1088070 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1034396 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0455. Min Act: -0.1700

Data Index: 489783 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0139. Min Act: -0.1700

Data Index: 9446 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0455. Min Act: -0.1700

Data Index: 750834 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.0928. Min Range: -3.0928

Max Act: 2.9664. Min Act: -0.1700

Data Index: 1191630 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0139. Min Act: -0.1700

Data Index: 567487 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0139. Min Act: -0.1700

Data Index: 66496 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.0928. Min Range: -3.0928

Max Act: 3.0612. Min Act: -0.1700

Data Index: 602713 (C4 (Web Text))

Max Activating Token Index: 767