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

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

Neuron 131 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: 3.9251. Min Range: -3.9251

Max Act: 3.9251. Min Act: -0.1700

Data Index: 599297 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.9251. Min Act: -0.1700

Data Index: 650481 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8938. Min Act: -0.1700

Data Index: 810633 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8625. Min Act: -0.1700

Data Index: 579364 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.9251. Min Act: -0.1700

Data Index: 803325 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8938. Min Act: -0.1700

Data Index: 59107 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8000. Min Act: -0.1700

Data Index: 710067 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8313. Min Act: -0.1700

Data Index: 1259246 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8313. Min Act: -0.1700

Data Index: 221506 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8625. Min Act: -0.1700

Data Index: 482001 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8000. Min Act: -0.1700

Data Index: 315742 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.8000. Min Act: -0.1700

Data Index: 1203721 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7687. Min Act: -0.1700

Data Index: 755574 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7374. Min Act: -0.1700

Data Index: 1059411 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7374. Min Act: -0.1700

Data Index: 871030 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7687. Min Act: -0.1700

Data Index: 38443 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7687. Min Act: -0.1700

Data Index: 978028 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7374. Min Act: -0.1700

Data Index: 730182 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7374. Min Act: -0.1700

Data Index: 372593 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 3.9251. Min Range: -3.9251

Max Act: 3.7374. Min Act: -0.1700

Data Index: 112282 (C4 (Web Text))

Max Activating Token Index: 857