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

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

Neuron 1357 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1516. Min Range: -5.1516

Max Act: 5.1516. Min Act: -0.1700

Data Index: 22057 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.8391. Min Act: -0.1700

Data Index: 803534 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.8078. Min Act: -0.1700

Data Index: 1252316 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.7141. Min Act: -0.1700

Data Index: 1229969 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.7453. Min Act: -0.1700

Data Index: 749849 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.7141. Min Act: -0.1700

Data Index: 1012574 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6516. Min Act: -0.1700

Data Index: 414452 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6828. Min Act: -0.1700

Data Index: 18456 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6828. Min Act: -0.1700

Data Index: 499012 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6516. Min Act: -0.1700

Data Index: 1244568 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6203. Min Act: -0.1700

Data Index: 844137 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6203. Min Act: -0.1700

Data Index: 26631 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6516. Min Act: -0.1700

Data Index: 130485 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6516. Min Act: -0.1700

Data Index: 7548 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6516. Min Act: -0.1700

Data Index: 294475 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6203. Min Act: -0.1700

Data Index: 239781 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6203. Min Act: -0.1700

Data Index: 1082342 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.5891. Min Act: -0.1700

Data Index: 1103727 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6203. Min Act: -0.1700

Data Index: 401676 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 5.1516. Min Range: -5.1516

Max Act: 4.6516. Min Act: -0.1700

Data Index: 1174760 (C4 (Web Text))

Max Activating Token Index: 445