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

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

Neuron 891 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: 7.6139. Min Range: -7.6139

Max Act: 7.6139. Min Act: -0.1700

Data Index: 366845 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 7.6139. Min Range: -7.6139

Max Act: 6.3014. Min Act: -0.1700

Data Index: 58495 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 7.6139. Min Range: -7.6139

Max Act: 6.2701. Min Act: -0.1700

Data Index: 706650 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 7.6139. Min Range: -7.6139

Max Act: 6.1451. Min Act: -0.1700

Data Index: 1042917 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 7.6139. Min Range: -7.6139

Max Act: 6.1139. Min Act: -0.1700

Data Index: 781986 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.9889. Min Act: -0.1700

Data Index: 935596 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 7.6139. Min Range: -7.6139

Max Act: 6.0201. Min Act: -0.1700

Data Index: 995650 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.9889. Min Act: -0.1700

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8639. Min Act: -0.1700

Data Index: 579645 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8639. Min Act: -0.1700

Data Index: 741011 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8326. Min Act: -0.1700

Data Index: 529930 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8639. Min Act: -0.1700

Data Index: 696032 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8014. Min Act: -0.1700

Data Index: 602040 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8326. Min Act: -0.1700

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.7701. Min Act: -0.1700

Data Index: 105203 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.7701. Min Act: -0.1700

Data Index: 1349014 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.7701. Min Act: -0.1700

Data Index: 1005014 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.7076. Min Act: -0.1700

Data Index: 1256609 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.7076. Min Act: -0.1700

Data Index: 887999 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 7.6139. Min Range: -7.6139

Max Act: 5.8014. Min Act: -0.1700

Data Index: 444466 (C4 (Web Text))

Max Activating Token Index: 634