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

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

Neuron 1526 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.7724. Min Act: -0.1700

Data Index: 1232965 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.6785. Min Act: -0.1700

Data Index: 63006 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1107267 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.6315. Min Act: -0.1700

Data Index: 315033 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.6315. Min Act: -0.1700

Data Index: 305629 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.6472. Min Act: -0.1700

Data Index: 875933 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5689. Min Act: -0.1700

Data Index: 364852 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5689. Min Act: -0.1700

Data Index: 703307 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.6159. Min Act: -0.1700

Data Index: 996941 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1066541 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5376. Min Act: -0.1700

Data Index: 735444 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5376. Min Act: -0.1700

Data Index: 230880 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1308208 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5219. Min Act: -0.1700

Data Index: 293672 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5532. Min Act: -0.1700

Data Index: 391338 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5062. Min Act: -0.1700

Data Index: 794639 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.4906. Min Act: -0.1700

Data Index: 81005 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5532. Min Act: -0.1700

Data Index: 494621 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5062. Min Act: -0.1700

Data Index: 300443 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 3.7724. Min Range: -3.7724

Max Act: 3.5219. Min Act: -0.1700

Data Index: 977102 (C4 (Web Text))

Max Activating Token Index: 342