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

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

Neuron 396 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: 5.3141. Min Range: -5.3141

Max Act: 5.3141. Min Act: -0.1700

Data Index: 720967 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.2829. Min Act: -0.1700

Data Index: 116118 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.1266. Min Act: -0.1700

Data Index: 733259 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.1266. Min Act: -0.1700

Data Index: 477877 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.1266. Min Act: -0.1700

Data Index: 273537 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.0954. Min Act: -0.1700

Data Index: 981827 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.0641. Min Act: -0.1700

Data Index: 487380 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.0954. Min Act: -0.1700

Data Index: 764409 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.0641. Min Act: -0.1700

Data Index: 174659 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.0329. Min Act: -0.1700

Data Index: 728111 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9704. Min Act: -0.1700

Data Index: 857857 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9391. Min Act: -0.1700

Data Index: 151955 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9391. Min Act: -0.1700

Data Index: 789829 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9704. Min Act: -0.1700

Data Index: 144558 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9391. Min Act: -0.1700

Data Index: 1144640 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9078. Min Act: -0.1700

Data Index: 413777 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9704. Min Act: -0.1700

Data Index: 1310956 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9078. Min Act: -0.1700

Data Index: 889606 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 5.3141. Min Range: -5.3141

Max Act: 4.9391. Min Act: -0.1700

Data Index: 100957 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 5.3141. Min Range: -5.3141

Max Act: 5.0016. Min Act: -0.1700

Data Index: 905652 (C4 (Web Text))

Max Activating Token Index: 467