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

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

Neuron 1656 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: 3.3098. Min Range: -3.3098

Max Act: 3.3098. Min Act: -0.1700

Data Index: 1305281 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.2470. Min Act: -0.1700

Data Index: 106160 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1998. Min Act: -0.1700

Data Index: 288953 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1841. Min Act: -0.1700

Data Index: 1052673 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1368. Min Act: -0.1700

Data Index: 1103253 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1368. Min Act: -0.1700

Data Index: 532531 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1211. Min Act: -0.1700

Data Index: 940743 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1368. Min Act: -0.1700

Data Index: 869979 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1053. Min Act: -0.1700

Data Index: 395139 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 123929 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 223785 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1211. Min Act: -0.1700

Data Index: 369604 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.1053. Min Act: -0.1700

Data Index: 85654 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0738. Min Act: -0.1700

Data Index: 649106 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1108324 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 358674 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1147538 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 115095 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0895. Min Act: -0.1700

Data Index: 302630 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 3.3098. Min Range: -3.3098

Max Act: 3.0738. Min Act: -0.1700

Data Index: 813623 (C4 (Web Text))

Max Activating Token Index: 306