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

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

Neuron 1832 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: 3.7654. Min Range: -3.7654

Max Act: 3.7654. Min Act: -0.1700

Data Index: 682361 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.7341. Min Act: -0.1700

Data Index: 1016944 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.7029. Min Act: -0.1700

Data Index: 501260 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6403. Min Act: -0.1700

Data Index: 496997 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6089. Min Act: -0.1700

Data Index: 806006 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6716. Min Act: -0.1700

Data Index: 439703 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5776. Min Act: -0.1700

Data Index: 832719 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5463. Min Act: -0.1700

Data Index: 784847 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6089. Min Act: -0.1700

Data Index: 793796 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.6089. Min Act: -0.1700

Data Index: 631944 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5463. Min Act: -0.1700

Data Index: 465166 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5463. Min Act: -0.1700

Data Index: 349655 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5463. Min Act: -0.1700

Data Index: 720035 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5150. Min Act: -0.1700

Data Index: 980232 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5150. Min Act: -0.1700

Data Index: 490592 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5776. Min Act: -0.1700

Data Index: 549598 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.4836. Min Act: -0.1700

Data Index: 997268 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.4523. Min Act: -0.1700

Data Index: 917239 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.5150. Min Act: -0.1700

Data Index: 522200 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.7654. Min Range: -3.7654

Max Act: 3.4836. Min Act: -0.1700

Data Index: 900666 (C4 (Web Text))

Max Activating Token Index: 685