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

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

Neuron 556 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: 3.8139. Min Range: -3.8139

Max Act: 3.8139. Min Act: -0.1700

Data Index: 115196 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7826. Min Act: -0.1700

Data Index: 552678 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.8139. Min Act: -0.1700

Data Index: 597252 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.8139. Min Act: -0.1700

Data Index: 413888 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7826. Min Act: -0.1700

Data Index: 1600851 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 1061260 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7514. Min Act: -0.1700

Data Index: 1053906 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7826. Min Act: -0.1700

Data Index: 229770 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 721327 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 301977 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 450069 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 591124 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7514. Min Act: -0.1700

Data Index: 45822 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 706631 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7514. Min Act: -0.1700

Data Index: 865203 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 810525 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.6888. Min Act: -0.1700

Data Index: 535997 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.7201. Min Act: -0.1700

Data Index: 31750 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.6888. Min Act: -0.1700

Data Index: 749563 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.8139. Min Range: -3.8139

Max Act: 3.6888. Min Act: -0.1700

Data Index: 690068 (C4 (Web Text))

Max Activating Token Index: 308