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

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

Neuron 1873 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: 7.2571. Min Range: -7.2571

Max Act: 7.2571. Min Act: -0.1700

Data Index: 333498 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 7.2571. Min Range: -7.2571

Max Act: 7.1321. Min Act: -0.1700

Data Index: 1310262 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 7.2571. Min Range: -7.2571

Max Act: 7.1008. Min Act: -0.1700

Data Index: 23656 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 7.2571. Min Range: -7.2571

Max Act: 7.0383. Min Act: -0.1700

Data Index: 538249 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 7.2571. Min Range: -7.2571

Max Act: 7.0696. Min Act: -0.1700

Data Index: 621514 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 7.2571. Min Range: -7.2571

Max Act: 7.0696. Min Act: -0.1700

Data Index: 561249 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.9446. Min Act: -0.1700

Data Index: 827566 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.9758. Min Act: -0.1700

Data Index: 1268843 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.9758. Min Act: -0.1700

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.9446. Min Act: -0.1700

Data Index: 705078 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.9446. Min Act: -0.1700

Data Index: 682377 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.9133. Min Act: -0.1700

Data Index: 1066617 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.8821. Min Act: -0.1700

Data Index: 1050526 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.8508. Min Act: -0.1700

Data Index: 947872 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.7571. Min Act: -0.1700

Data Index: 241537 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.7571. Min Act: -0.1700

Data Index: 197168 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.7571. Min Act: -0.1700

Data Index: 13034 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.7571. Min Act: -0.1700

Data Index: 161852 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.7571. Min Act: -0.1700

Data Index: 1024301 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 7.2571. Min Range: -7.2571

Max Act: 6.7258. Min Act: -0.1700

Data Index: 740753 (C4 (Web Text))

Max Activating Token Index: 309