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

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

Neuron 1378 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: 5.6102. Min Range: -5.6102

Max Act: 5.6102. Min Act: -0.1700

Data Index: 338407 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.3290. Min Act: -0.1700

Data Index: 1117869 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.4227. Min Act: -0.1700

Data Index: 565497 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.4852. Min Act: -0.1700

Data Index: 548335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.2977. Min Act: -0.1700

Data Index: 494646 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.2977. Min Act: -0.1700

Data Index: 1353386 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.2665. Min Act: -0.1700

Data Index: 112800 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.2352. Min Act: -0.1700

Data Index: 997566 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.1102. Min Act: -0.1700

Data Index: 1136197 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.2977. Min Act: -0.1700

Data Index: 262247 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.0165. Min Act: -0.1700

Data Index: 939128 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 5.6102. Min Range: -5.6102

Max Act: 4.8290. Min Act: -0.1700

Data Index: 277676 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.1102. Min Act: -0.1700

Data Index: 1149839 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.1415. Min Act: -0.1700

Data Index: 106159 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 5.6102. Min Range: -5.6102

Max Act: 5.0790. Min Act: -0.1700

Data Index: 664001 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 5.6102. Min Range: -5.6102

Max Act: 4.9852. Min Act: -0.1700

Data Index: 393603 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 5.6102. Min Range: -5.6102

Max Act: 4.9540. Min Act: -0.1700

Data Index: 1178612 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 5.6102. Min Range: -5.6102

Max Act: 4.9227. Min Act: -0.1700

Data Index: 970072 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 5.6102. Min Range: -5.6102

Max Act: 4.9227. Min Act: -0.1700

Data Index: 35129 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 5.6102. Min Range: -5.6102

Max Act: 4.8915. Min Act: -0.1700

Data Index: 87303 (C4 (Web Text))

Max Activating Token Index: 903