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

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

Neuron 739 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.6419. Min Act: -0.1700

Data Index: 796809 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.6157. Min Act: -0.1697

Data Index: 1100310 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5983. Min Act: -0.1700

Data Index: 846114 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5721. Min Act: -0.1699

Data Index: 809403 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5721. Min Act: -0.1697

Data Index: 127650 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5546. Min Act: -0.1698

Data Index: 282059 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5458. Min Act: -0.1700

Data Index: 405835 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5458. Min Act: -0.1699

Data Index: 740863 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5371. Min Act: -0.1700

Data Index: 1157262 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5371. Min Act: -0.1697

Data Index: 692688 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5283. Min Act: -0.1698

Data Index: 983767 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5283. Min Act: -0.1697

Data Index: 604729 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5195. Min Act: -0.1697

Data Index: 33073 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5108. Min Act: -0.1699

Data Index: 335459 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5020. Min Act: -0.1700

Data Index: 39826 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5108. Min Act: -0.1697

Data Index: 651448 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5020. Min Act: -0.1699

Data Index: 543873 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5020. Min Act: -0.1697

Data Index: 1003792 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5020. Min Act: -0.1699

Data Index: 870318 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.6419. Min Range: -1.6419

Max Act: 1.5108. Min Act: -0.1697

Data Index: 32005 (C4 (Web Text))

Max Activating Token Index: 967