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

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

Neuron 757 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: 4.1558. Min Range: -4.1558

Max Act: 4.1558. Min Act: -0.1700

Data Index: 204004 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.9369. Min Act: -0.1700

Data Index: 1039767 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.8118. Min Act: -0.1699

Data Index: 1158175 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.9056. Min Act: -0.1700

Data Index: 912616 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.7805. Min Act: -0.1700

Data Index: 1069038 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.7492. Min Act: -0.1700

Data Index: 241141 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6867. Min Act: -0.1699

Data Index: 1320056 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.7492. Min Act: -0.1700

Data Index: 201189 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.7805. Min Act: -0.1700

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6867. Min Act: -0.1700

Data Index: 1087294 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.7180. Min Act: -0.1700

Data Index: 1198168 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6867. Min Act: -0.1700

Data Index: 46004 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6241. Min Act: -0.1699

Data Index: 617868 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6554. Min Act: -0.1700

Data Index: 982501 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.7180. Min Act: -0.1700

Data Index: 492128 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6867. Min Act: -0.1700

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6867. Min Act: -0.1700

Data Index: 872783 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6554. Min Act: -0.1700

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6867. Min Act: -0.1700

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.5927. Min Act: -0.1700

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 759