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

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

Neuron 82 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: 5.5377. Min Range: -5.5377

Max Act: 5.5377. Min Act: -0.1700

Data Index: 880611 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.2565. Min Act: -0.1700

Data Index: 3682 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.1940. Min Act: -0.1700

Data Index: 873898 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.1315. Min Act: -0.1700

Data Index: 1295710 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.0065. Min Act: -0.1700

Data Index: 663794 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.0065. Min Act: -0.1700

Data Index: 1613308 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.0377. Min Act: -0.1700

Data Index: 132369 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.9440. Min Act: -0.1700

Data Index: 1069133 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.9752. Min Act: -0.1700

Data Index: 649802 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 5.5377. Min Range: -5.5377

Max Act: 5.0377. Min Act: -0.1700

Data Index: 672034 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.9127. Min Act: -0.1700

Data Index: 991011 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.8815. Min Act: -0.1700

Data Index: 766204 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.9127. Min Act: -0.1700

Data Index: 73860 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.9440. Min Act: -0.1700

Data Index: 1251651 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.8502. Min Act: -0.1700

Data Index: 164188 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.8502. Min Act: -0.1700

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.8190. Min Act: -0.1700

Data Index: 1048269 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.7877. Min Act: -0.1700

Data Index: 958018 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.7877. Min Act: -0.1700

Data Index: 465951 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 5.5377. Min Range: -5.5377

Max Act: 4.7252. Min Act: -0.1700

Data Index: 665826 (C4 (Web Text))

Max Activating Token Index: 833