Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0521. Min Range: -5.0521

Max Act: 5.0521. Min Act: -0.1700

Data Index: 87104 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.8958. Min Act: -0.1700

Data Index: 1085043 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.7396. Min Act: -0.1700

Data Index: 898735 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.8021. Min Act: -0.1700

Data Index: 468177 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.7396. Min Act: -0.1700

Data Index: 48782 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.7396. Min Act: -0.1700

Data Index: 1046144 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.6771. Min Act: -0.1700

Data Index: 736962 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.6458. Min Act: -0.1700

Data Index: 390249 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.7083. Min Act: -0.1700

Data Index: 868383 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.6146. Min Act: -0.1700

Data Index: 294686 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5833. Min Act: -0.1700

Data Index: 384718 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5833. Min Act: -0.1700

Data Index: 959188 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5833. Min Act: -0.1700

Data Index: 414031 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5521. Min Act: -0.1700

Data Index: 980787 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.4895. Min Act: -0.1700

Data Index: 1195732 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5208. Min Act: -0.1700

Data Index: 533232 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5833. Min Act: -0.1700

Data Index: 770722 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5833. Min Act: -0.1700

Data Index: 160884 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5521. Min Act: -0.1700

Data Index: 848216 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 5.0521. Min Range: -5.0521

Max Act: 4.5521. Min Act: -0.1700

Data Index: 1078335 (C4 (Web Text))

Max Activating Token Index: 797