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

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

Neuron 1250 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: 5.7078. Min Range: -5.7078

Max Act: 5.7078. Min Act: -0.1700

Data Index: 324265 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.6141. Min Act: -0.1700

Data Index: 1000460 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.5516. Min Act: -0.1700

Data Index: 808564 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.5828. Min Act: -0.1700

Data Index: 39774 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.5516. Min Act: -0.1700

Data Index: 909014 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.5203. Min Act: -0.1700

Data Index: 945950 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3953. Min Act: -0.1700

Data Index: 825417 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.4266. Min Act: -0.1700

Data Index: 95483 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.4266. Min Act: -0.1700

Data Index: 356182 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3953. Min Act: -0.1700

Data Index: 377565 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3953. Min Act: -0.1700

Data Index: 179531 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3641. Min Act: -0.1700

Data Index: 1147664 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3016. Min Act: -0.1700

Data Index: 463384 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3016. Min Act: -0.1700

Data Index: 727887 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.2703. Min Act: -0.1700

Data Index: 569626 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.2703. Min Act: -0.1700

Data Index: 561906 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3016. Min Act: -0.1700

Data Index: 1250705 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3016. Min Act: -0.1700

Data Index: 952003 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3016. Min Act: -0.1700

Data Index: 1067977 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 5.7078. Min Range: -5.7078

Max Act: 5.3016. Min Act: -0.1700

Data Index: 160996 (C4 (Web Text))

Max Activating Token Index: 490