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

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

Neuron 326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.4453. Min Act: -0.1700

Data Index: 88800 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.3203. Min Act: -0.1700

Data Index: 540373 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.2578. Min Act: -0.1700

Data Index: 1333458 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.2265. Min Act: -0.1698

Data Index: 511965 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.2578. Min Act: -0.1700

Data Index: 945790 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.1328. Min Act: -0.1700

Data Index: 334907 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.1015. Min Act: -0.1700

Data Index: 721377 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.1015. Min Act: -0.1700

Data Index: 1005742 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0703. Min Act: -0.1700

Data Index: 553716 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.1015. Min Act: -0.1700

Data Index: 1034551 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0703. Min Act: -0.1700

Data Index: 675438 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0390. Min Act: -0.1700

Data Index: 134661 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0390. Min Act: -0.1700

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0703. Min Act: -0.1700

Data Index: 1191998 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0390. Min Act: -0.1700

Data Index: 1204988 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0390. Min Act: -0.1606

Data Index: 1226508 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0390. Min Act: -0.1699

Data Index: 422703 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0390. Min Act: -0.1700

Data Index: 587593 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 5.4453. Min Range: -5.4453

Max Act: 5.0078. Min Act: -0.1700

Data Index: 358348 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 5.4453. Min Range: -5.4453

Max Act: 4.9765. Min Act: -0.1695

Data Index: 785791 (C4 (Web Text))

Max Activating Token Index: 161