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

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

Neuron 491 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: 5.3844. Min Range: -5.3844

Max Act: 5.1813. Min Act: -0.1700

Data Index: 419734 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.3844. Min Act: -0.1700

Data Index: 871618 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.3063. Min Act: -0.1700

Data Index: 685535 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.2281. Min Act: -0.1700

Data Index: 1197581 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1813. Min Act: -0.1700

Data Index: 375391 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.2906. Min Act: -0.1700

Data Index: 90301 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1891. Min Act: -0.1700

Data Index: 977605 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1969. Min Act: -0.1700

Data Index: 599296 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1969. Min Act: -0.1700

Data Index: 198882 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.0641. Min Act: -0.1700

Data Index: 917717 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1656. Min Act: -0.1700

Data Index: 883501 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1500. Min Act: -0.1700

Data Index: 1177966 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1188. Min Act: -0.1700

Data Index: 439831 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1188. Min Act: -0.1700

Data Index: 586951 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.1031. Min Act: -0.1700

Data Index: 189305 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.0875. Min Act: -0.1700

Data Index: 855821 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.0875. Min Act: -0.1700

Data Index: 819174 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.0094. Min Act: -0.1700

Data Index: 1296712 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 5.3844. Min Range: -5.3844

Max Act: 5.0797. Min Act: -0.1700

Data Index: 681164 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 5.3844. Min Range: -5.3844

Max Act: 4.9703. Min Act: -0.1700

Data Index: 557031 (C4 (Web Text))

Max Activating Token Index: 349