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

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

Neuron 1884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.3729. Min Act: -0.1700

Data Index: 1207872 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.2792. Min Act: -0.1700

Data Index: 247938 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.2792. Min Act: -0.1700

Data Index: 475119 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.1542. Min Act: -0.1700

Data Index: 631282 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.0917. Min Act: -0.1700

Data Index: 503326 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.1854. Min Act: -0.1700

Data Index: 1124940 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.0917. Min Act: -0.1700

Data Index: 1038931 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.0604. Min Act: -0.1697

Data Index: 887599 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.9979. Min Act: -0.1700

Data Index: 414499 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.9667. Min Act: -0.1700

Data Index: 1088284 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 6.3729. Min Range: -6.3729

Max Act: 6.0604. Min Act: -0.1700

Data Index: 1094202 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.9979. Min Act: -0.1700

Data Index: 162872 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.9354. Min Act: -0.1700

Data Index: 1018256 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.8729. Min Act: -0.1700

Data Index: 1175758 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.8417. Min Act: -0.1700

Data Index: 135950 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.9042. Min Act: -0.1700

Data Index: 620307 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.8104. Min Act: -0.1700

Data Index: 504474 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.6542. Min Act: -0.1700

Data Index: 669727 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.7479. Min Act: -0.1696

Data Index: 5766 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 6.3729. Min Range: -6.3729

Max Act: 5.5917. Min Act: -0.1700

Data Index: 459918 (C4 (Web Text))

Max Activating Token Index: 452