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

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

Neuron 44 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.6141. Min Act: -0.1700

Data Index: 1333680 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.5516. Min Act: -0.1700

Data Index: 161422 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.4891. Min Act: -0.1700

Data Index: 898855 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.4891. Min Act: -0.1700

Data Index: 1302865 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.5204. Min Act: -0.1700

Data Index: 191453 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.4266. Min Act: -0.1700

Data Index: 363208 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3641. Min Act: -0.1700

Data Index: 1240703 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3641. Min Act: -0.1700

Data Index: 280261 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3954. Min Act: -0.1700

Data Index: 995315 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3329. Min Act: -0.1700

Data Index: 849629 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3329. Min Act: -0.1700

Data Index: 321846 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3641. Min Act: -0.1700

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3329. Min Act: -0.1700

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3016. Min Act: -0.1700

Data Index: 1060709 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3329. Min Act: -0.1700

Data Index: 561093 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3329. Min Act: -0.1700

Data Index: 1001395 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3329. Min Act: -0.1700

Data Index: 464949 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.3016. Min Act: -0.1700

Data Index: 751796 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.2704. Min Act: -0.1700

Data Index: 472126 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 5.6141. Min Range: -5.6141

Max Act: 5.2391. Min Act: -0.1700

Data Index: 712674 (C4 (Web Text))

Max Activating Token Index: 359