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

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

Neuron 1166 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: 5.5889. Min Range: -5.5889

Max Act: 5.5889. Min Act: -0.1700

Data Index: 669820 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.4014. Min Act: -0.1700

Data Index: 755287 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.4327. Min Act: -0.1700

Data Index: 1316031 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.4327. Min Act: -0.1700

Data Index: 290451 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.3389. Min Act: -0.1700

Data Index: 782401 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1204846 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.2139. Min Act: -0.1700

Data Index: 831734 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1514. Min Act: -0.1700

Data Index: 1139617 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 187513 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1514. Min Act: -0.1700

Data Index: 847375 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.2452. Min Act: -0.1700

Data Index: 225505 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1568251 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1497676 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1518139 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1113873 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1514. Min Act: -0.1700

Data Index: 842767 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1641646 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1492278 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0889. Min Act: -0.1700

Data Index: 1437216 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 5.5889. Min Range: -5.5889

Max Act: 5.0577. Min Act: -0.1700

Data Index: 662897 (C4 (Web Text))

Max Activating Token Index: 589