Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 775 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1066599 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1166. Min Act: -0.1700

Data Index: 945523 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1009. Min Act: -0.1700

Data Index: 961109 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.1009. Min Act: -0.1699

Data Index: 214192 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 501767 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 258230 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1328712 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0693. Min Act: -0.1700

Data Index: 27610 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0535. Min Act: -0.1700

Data Index: 64988 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0378. Min Act: -0.1700

Data Index: 634216 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0535. Min Act: -0.1700

Data Index: 1233902 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0220. Min Act: -0.1700

Data Index: 1179523 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0378. Min Act: -0.1700

Data Index: 1303005 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0378. Min Act: -0.1700

Data Index: 949999 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0220. Min Act: -0.1700

Data Index: 158381 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1256736 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0062. Min Act: -0.1700

Data Index: 1113802 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0220. Min Act: -0.1700

Data Index: 871219 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0062. Min Act: -0.1700

Data Index: 371840 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 3.1639. Min Range: -3.1639

Max Act: 3.0220. Min Act: -0.1700

Data Index: 94257 (C4 (Web Text))

Max Activating Token Index: 191