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

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

Neuron 251 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: 3.1778. Min Range: -3.1778

Max Act: 3.1778. Min Act: -0.1700

Data Index: 1292466 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.1778. Min Act: -0.1700

Data Index: 1159047 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0990. Min Act: -0.1700

Data Index: 598485 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0990. Min Act: -0.1700

Data Index: 229989 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0832. Min Act: -0.1700

Data Index: 307629 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0832. Min Act: -0.1700

Data Index: 746168 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0832. Min Act: -0.1700

Data Index: 967222 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0990. Min Act: -0.1700

Data Index: 355749 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0675. Min Act: -0.1700

Data Index: 616477 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0517. Min Act: -0.1700

Data Index: 367665 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0675. Min Act: -0.1700

Data Index: 476422 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0359. Min Act: -0.1700

Data Index: 1001902 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0990. Min Act: -0.1700

Data Index: 725492 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1030336 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0675. Min Act: -0.1700

Data Index: 660583 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0359. Min Act: -0.1700

Data Index: 521709 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1103595 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0517. Min Act: -0.1700

Data Index: 508318 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 3.1778. Min Range: -3.1778

Max Act: 3.0043. Min Act: -0.1700

Data Index: 1168379 (C4 (Web Text))

Max Activating Token Index: 303