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

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

Neuron 185 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: 3.9269. Min Range: -3.9269

Max Act: 3.9269. Min Act: -0.1700

Data Index: 828265 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.6923. Min Act: -0.1700

Data Index: 1089177 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.6140. Min Act: -0.1700

Data Index: 1089537 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.5827. Min Act: -0.1700

Data Index: 942360 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.5358. Min Act: -0.1700

Data Index: 199423 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.5201. Min Act: -0.1700

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4731. Min Act: -0.1700

Data Index: 714804 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4417. Min Act: -0.1700

Data Index: 543032 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1346186 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1138219 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4574. Min Act: -0.1700

Data Index: 1456814 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4417. Min Act: -0.1700

Data Index: 1053868 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4417. Min Act: -0.1700

Data Index: 1114784 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4574. Min Act: -0.1700

Data Index: 213257 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4260. Min Act: -0.1700

Data Index: 626489 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1262090 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4417. Min Act: -0.1700

Data Index: 1570690 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4104. Min Act: -0.1700

Data Index: 621646 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1540911 (Python Code)

Max Activating Token Index: 611

Text #19

Max Range: 3.9269. Min Range: -3.9269

Max Act: 3.4417. Min Act: -0.1700

Data Index: 542540 (C4 (Web Text))

Max Activating Token Index: 967