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

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

Neuron 377 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: 3.5531. Min Range: -3.5531

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1346506 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5218. Min Act: -0.1700

Data Index: 985371 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5531. Min Act: -0.1700

Data Index: 745496 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5218. Min Act: -0.1700

Data Index: 233913 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.5375. Min Act: -0.1700

Data Index: 211531 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4905. Min Act: -0.1700

Data Index: 865148 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4748. Min Act: -0.1700

Data Index: 692452 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4905. Min Act: -0.1700

Data Index: 558607 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4591. Min Act: -0.1700

Data Index: 1221071 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4591. Min Act: -0.1700

Data Index: 928996 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4591. Min Act: -0.1700

Data Index: 688922 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3964. Min Act: -0.1700

Data Index: 788577 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4278. Min Act: -0.1700

Data Index: 411471 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4121. Min Act: -0.1700

Data Index: 379299 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4121. Min Act: -0.1700

Data Index: 463906 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4121. Min Act: -0.1700

Data Index: 823986 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3964. Min Act: -0.1700

Data Index: 350783 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3807. Min Act: -0.1700

Data Index: 1094984 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.4278. Min Act: -0.1700

Data Index: 1059627 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.5531. Min Range: -3.5531

Max Act: 3.3964. Min Act: -0.1700

Data Index: 978756 (C4 (Web Text))

Max Activating Token Index: 444