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

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

Neuron 1873 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: 5.5102. Min Range: -5.5102

Max Act: 5.5102. Min Act: -0.1700

Data Index: 493469 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.2602. Min Act: -0.1700

Data Index: 714421 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.2602. Min Act: -0.1700

Data Index: 385018 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 1123954 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 622081 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1664. Min Act: -0.1700

Data Index: 162795 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1664. Min Act: -0.1700

Data Index: 936641 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1977. Min Act: -0.1700

Data Index: 867935 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.0727. Min Act: -0.1700

Data Index: 179243 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1664. Min Act: -0.1700

Data Index: 973755 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1664. Min Act: -0.1700

Data Index: 262292 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 328129 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 268262 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 619957 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 54729 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1039. Min Act: -0.1700

Data Index: 231914 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.1352. Min Act: -0.1700

Data Index: 104954 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 5.5102. Min Range: -5.5102

Max Act: 4.9789. Min Act: -0.1700

Data Index: 65283 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.0414. Min Act: -0.1700

Data Index: 689383 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 5.5102. Min Range: -5.5102

Max Act: 5.0414. Min Act: -0.1700

Data Index: 25522 (C4 (Web Text))

Max Activating Token Index: 783