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

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

Neuron 488 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: 5.5909. Min Range: -5.5909

Max Act: 5.5909. Min Act: -0.1700

Data Index: 794668 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.4347. Min Act: -0.1700

Data Index: 103415 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.3097. Min Act: -0.1700

Data Index: 818102 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.1847. Min Act: -0.1700

Data Index: 897723 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.2472. Min Act: -0.1700

Data Index: 400085 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.1847. Min Act: -0.1700

Data Index: 481384 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.1534. Min Act: -0.1700

Data Index: 313541 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.1847. Min Act: -0.1700

Data Index: 1289722 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.1534. Min Act: -0.1700

Data Index: 359042 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0909. Min Act: -0.1700

Data Index: 1288991 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0284. Min Act: -0.1700

Data Index: 685040 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0909. Min Act: -0.1700

Data Index: 759185 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0909. Min Act: -0.1700

Data Index: 394466 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0597. Min Act: -0.1700

Data Index: 894124 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0597. Min Act: -0.1700

Data Index: 75047 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0909. Min Act: -0.1700

Data Index: 37816 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 5.5909. Min Range: -5.5909

Max Act: 5.0284. Min Act: -0.1700

Data Index: 621146 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 5.5909. Min Range: -5.5909

Max Act: 4.9659. Min Act: -0.1700

Data Index: 704238 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 5.5909. Min Range: -5.5909

Max Act: 4.9659. Min Act: -0.1700

Data Index: 1000360 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 5.5909. Min Range: -5.5909

Max Act: 4.9347. Min Act: -0.1700

Data Index: 451189 (C4 (Web Text))

Max Activating Token Index: 440