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

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

Neuron 619 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: 5.2563. Min Range: -5.2563

Max Act: 5.2563. Min Act: -0.1700

Data Index: 416055 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.1313. Min Act: -0.1700

Data Index: 1181971 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.1938. Min Act: -0.1700

Data Index: 1077022 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.1938. Min Act: -0.1700

Data Index: 392826 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.1001. Min Act: -0.1699

Data Index: 470838 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.1001. Min Act: -0.1700

Data Index: 717215 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.0688. Min Act: -0.1700

Data Index: 996175 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.0688. Min Act: -0.1699

Data Index: 521058 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.0376. Min Act: -0.1699

Data Index: 404878 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.0063. Min Act: -0.1690

Data Index: 250815 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9751. Min Act: -0.1699

Data Index: 881993 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9751. Min Act: -0.1700

Data Index: 110749 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.0063. Min Act: -0.1699

Data Index: 317872 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 5.2563. Min Range: -5.2563

Max Act: 5.0063. Min Act: -0.1700

Data Index: 98762 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9438. Min Act: -0.1700

Data Index: 431894 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9438. Min Act: -0.1700

Data Index: 733096 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9438. Min Act: -0.1700

Data Index: 1144236 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9126. Min Act: -0.1700

Data Index: 1097991 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9126. Min Act: -0.1700

Data Index: 635248 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 5.2563. Min Range: -5.2563

Max Act: 4.9126. Min Act: -0.1700

Data Index: 1127174 (C4 (Web Text))

Max Activating Token Index: 298