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

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

Neuron 302 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: 5.8437. Min Range: -5.8437

Max Act: 5.8437. Min Act: -0.1700

Data Index: 1342398 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.7500. Min Act: -0.1700

Data Index: 449120 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.7500. Min Act: -0.1700

Data Index: 644794 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.7812. Min Act: -0.1700

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.6562. Min Act: -0.1700

Data Index: 254319 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.6250. Min Act: -0.1700

Data Index: 595598 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.7187. Min Act: -0.1700

Data Index: 1274604 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5937. Min Act: -0.1699

Data Index: 1285991 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.6562. Min Act: -0.1700

Data Index: 1009514 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5625. Min Act: -0.1700

Data Index: 175330 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5937. Min Act: -0.1700

Data Index: 944403 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.6562. Min Act: -0.1700

Data Index: 234812 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5312. Min Act: -0.1700

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5625. Min Act: -0.1700

Data Index: 466546 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5312. Min Act: -0.1700

Data Index: 1284243 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5937. Min Act: -0.1700

Data Index: 785065 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.6250. Min Act: -0.1700

Data Index: 107857 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.6250. Min Act: -0.1700

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5312. Min Act: -0.1700

Data Index: 1160503 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 5.8437. Min Range: -5.8437

Max Act: 5.5312. Min Act: -0.1700

Data Index: 672204 (C4 (Web Text))

Max Activating Token Index: 260