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

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

Neuron 1062 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.3703. Min Act: -0.1700

Data Index: 1287821 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.2918. Min Act: -0.1700

Data Index: 644311 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1817. Min Act: -0.1700

Data Index: 561614 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1817. Min Act: -0.1700

Data Index: 279886 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1660. Min Act: -0.1700

Data Index: 334073 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1502. Min Act: -0.1700

Data Index: 508901 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1502. Min Act: -0.1700

Data Index: 865690 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1502. Min Act: -0.1700

Data Index: 148801 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1502. Min Act: -0.1700

Data Index: 1155492 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1345. Min Act: -0.1700

Data Index: 920979 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1187. Min Act: -0.1700

Data Index: 1076721 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1030. Min Act: -0.1700

Data Index: 501586 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1345. Min Act: -0.1700

Data Index: 86952 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1030. Min Act: -0.1700

Data Index: 802769 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1030. Min Act: -0.1700

Data Index: 1046946 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.1187. Min Act: -0.1700

Data Index: 133500 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.0872. Min Act: -0.1700

Data Index: 726893 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.0872. Min Act: -0.1700

Data Index: 449511 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.0556. Min Act: -0.1700

Data Index: 398931 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.3703. Min Range: -3.3703

Max Act: 3.0714. Min Act: -0.1700

Data Index: 151629 (C4 (Web Text))

Max Activating Token Index: 922