Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1686 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7876. Min Act: -0.1700

Data Index: 1196051 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7563. Min Act: -0.1700

Data Index: 336828 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7876. Min Act: -0.1700

Data Index: 943763 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.7250. Min Act: -0.1700

Data Index: 297446 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6624. Min Act: -0.1700

Data Index: 33828 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6937. Min Act: -0.1700

Data Index: 28878 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6311. Min Act: -0.1700

Data Index: 751992 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6624. Min Act: -0.1700

Data Index: 1098591 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6624. Min Act: -0.1700

Data Index: 1125180 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6624. Min Act: -0.1700

Data Index: 122749 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6624. Min Act: -0.1700

Data Index: 921272 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6311. Min Act: -0.1700

Data Index: 380972 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5998. Min Act: -0.1700

Data Index: 744943 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.6311. Min Act: -0.1700

Data Index: 1352354 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5685. Min Act: -0.1700

Data Index: 1352151 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5998. Min Act: -0.1700

Data Index: 1183297 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5685. Min Act: -0.1700

Data Index: 1091941 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5998. Min Act: -0.1700

Data Index: 225051 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5685. Min Act: -0.1700

Data Index: 310608 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.7876. Min Range: -3.7876

Max Act: 3.5372. Min Act: -0.1700

Data Index: 334106 (C4 (Web Text))

Max Activating Token Index: 854