Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.8694. Min Act: -0.1700

Data Index: 397015 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.8381. Min Act: -0.1700

Data Index: 443806 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7756. Min Act: -0.1700

Data Index: 550000 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7444. Min Act: -0.1700

Data Index: 627032 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7131. Min Act: -0.1700

Data Index: 113992 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7444. Min Act: -0.1700

Data Index: 1250299 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7756. Min Act: -0.1700

Data Index: 146043 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7444. Min Act: -0.1700

Data Index: 524795 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7444. Min Act: -0.1700

Data Index: 89219 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7131. Min Act: -0.1700

Data Index: 971944 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7131. Min Act: -0.1700

Data Index: 497433 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6819. Min Act: -0.1700

Data Index: 962962 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7444. Min Act: -0.1700

Data Index: 1072549 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6506. Min Act: -0.1700

Data Index: 1249941 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6819. Min Act: -0.1700

Data Index: 409202 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6819. Min Act: -0.1700

Data Index: 167398 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6506. Min Act: -0.1700

Data Index: 1333631 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.7131. Min Act: -0.1695

Data Index: 1282136 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6506. Min Act: -0.1700

Data Index: 332677 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 5.8694. Min Range: -5.8694

Max Act: 5.6819. Min Act: -0.1700

Data Index: 794854 (C4 (Web Text))

Max Activating Token Index: 220