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

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

Neuron 1601 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: 5.7750. Min Range: -5.7750

Max Act: 5.7750. Min Act: -0.1700

Data Index: 687836 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2750. Min Act: -0.1700

Data Index: 1123908 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2750. Min Act: -0.1700

Data Index: 766527 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2750. Min Act: -0.1700

Data Index: 44242 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2125. Min Act: -0.1700

Data Index: 780652 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2438. Min Act: -0.1700

Data Index: 285624 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2750. Min Act: -0.1700

Data Index: 871476 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1813. Min Act: -0.1700

Data Index: 1358438 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1813. Min Act: -0.1700

Data Index: 12588 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1813. Min Act: -0.1700

Data Index: 658815 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1813. Min Act: -0.1700

Data Index: 724292 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1813. Min Act: -0.1700

Data Index: 864666 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.2125. Min Act: -0.1699

Data Index: 634310 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1813. Min Act: -0.1700

Data Index: 237478 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1188. Min Act: -0.1700

Data Index: 933014 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1188. Min Act: -0.1700

Data Index: 93279 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1188. Min Act: -0.1700

Data Index: 1177308 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.1500. Min Act: -0.1700

Data Index: 290236 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.0563. Min Act: -0.1700

Data Index: 443412 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 5.7750. Min Range: -5.7750

Max Act: 5.0875. Min Act: -0.1700

Data Index: 984442 (C4 (Web Text))

Max Activating Token Index: 768