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

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

Neuron 1919 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.7880. Min Act: -0.1700

Data Index: 451782 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.6629. Min Act: -0.1700

Data Index: 1296030 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5689. Min Act: -0.1700

Data Index: 881366 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5689. Min Act: -0.1700

Data Index: 818484 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5376. Min Act: -0.1700

Data Index: 758863 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1064154 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5063. Min Act: -0.1700

Data Index: 626685 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1141949 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5063. Min Act: -0.1700

Data Index: 764123 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5063. Min Act: -0.1700

Data Index: 190274 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5376. Min Act: -0.1699

Data Index: 19861 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.5063. Min Act: -0.1700

Data Index: 23777 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4436. Min Act: -0.1700

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4436. Min Act: -0.1700

Data Index: 1329357 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4749. Min Act: -0.1700

Data Index: 880078 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4122. Min Act: -0.1700

Data Index: 565273 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4436. Min Act: -0.1700

Data Index: 798543 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.3809. Min Act: -0.1700

Data Index: 32506 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4436. Min Act: -0.1700

Data Index: 226301 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 3.7880. Min Range: -3.7880

Max Act: 3.4122. Min Act: -0.1700

Data Index: 856572 (C4 (Web Text))

Max Activating Token Index: 602