Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 6.0629. Min Range: -6.0629

Max Act: 6.0629. Min Act: -0.1700

Data Index: 1204805 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 6.0629. Min Range: -6.0629

Max Act: 6.0004. Min Act: -0.1700

Data Index: 1143443 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9692. Min Act: -0.1700

Data Index: 370488 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9379. Min Act: -0.1700

Data Index: 1037291 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9692. Min Act: -0.1700

Data Index: 957133 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9067. Min Act: -0.1700

Data Index: 984679 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9067. Min Act: -0.1700

Data Index: 241097 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9379. Min Act: -0.1700

Data Index: 198737 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9692. Min Act: -0.1700

Data Index: 1339049 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9067. Min Act: -0.1700

Data Index: 1358586 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9379. Min Act: -0.1700

Data Index: 592486 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9379. Min Act: -0.1700

Data Index: 598625 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9067. Min Act: -0.1700

Data Index: 224289 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9067. Min Act: -0.1700

Data Index: 12978 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.8754. Min Act: -0.1700

Data Index: 48093 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9379. Min Act: -0.1700

Data Index: 585395 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9692. Min Act: -0.1700

Data Index: 188094 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.9379. Min Act: -0.1700

Data Index: 320646 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.8442. Min Act: -0.1700

Data Index: 223470 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 6.0629. Min Range: -6.0629

Max Act: 5.8442. Min Act: -0.1700

Data Index: 999889 (C4 (Web Text))

Max Activating Token Index: 30