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

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

Neuron 505 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: 5.3955. Min Range: -5.3955

Max Act: 5.3955. Min Act: -0.1700

Data Index: 360791 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.3017. Min Act: -0.1700

Data Index: 553695 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.2080. Min Act: -0.1700

Data Index: 1031909 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.2080. Min Act: -0.1700

Data Index: 171726 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.2080. Min Act: -0.1700

Data Index: 927089 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1767. Min Act: -0.1700

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.2080. Min Act: -0.1700

Data Index: 1273333 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1767. Min Act: -0.1700

Data Index: 122585 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1455. Min Act: -0.1700

Data Index: 419649 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1455. Min Act: -0.1700

Data Index: 1073204 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1767. Min Act: -0.1700

Data Index: 68646 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1455. Min Act: -0.1700

Data Index: 1158443 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.2080. Min Act: -0.1700

Data Index: 588866 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.0205. Min Act: -0.1700

Data Index: 441633 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1455. Min Act: -0.1700

Data Index: 9914 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1455. Min Act: -0.1700

Data Index: 205723 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.0517. Min Act: -0.1700

Data Index: 382770 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1142. Min Act: -0.1700

Data Index: 70850 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.0830. Min Act: -0.1700

Data Index: 790595 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 5.3955. Min Range: -5.3955

Max Act: 5.1767. Min Act: -0.1700

Data Index: 225716 (C4 (Web Text))

Max Activating Token Index: 597