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

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

Neuron 315 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9477. Min Act: -0.1700

Data Index: 766968 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9789. Min Act: -0.1700

Data Index: 670197 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9164. Min Act: -0.1700

Data Index: 159662 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9789. Min Act: -0.1700

Data Index: 1038936 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9477. Min Act: -0.1700

Data Index: 367375 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9164. Min Act: -0.1700

Data Index: 77161 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9164. Min Act: -0.1700

Data Index: 1280064 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8851. Min Act: -0.1700

Data Index: 1293773 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9164. Min Act: -0.1700

Data Index: 1129528 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8851. Min Act: -0.1700

Data Index: 915642 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9164. Min Act: -0.1700

Data Index: 281918 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9164. Min Act: -0.1700

Data Index: 855846 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8851. Min Act: -0.1700

Data Index: 397393 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8539. Min Act: -0.1700

Data Index: 366729 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8851. Min Act: -0.1700

Data Index: 709958 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8851. Min Act: -0.1700

Data Index: 93325 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8851. Min Act: -0.1700

Data Index: 1229656 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8539. Min Act: -0.1700

Data Index: 882551 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8226. Min Act: -0.1700

Data Index: 247797 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8539. Min Act: -0.1700

Data Index: 262468 (C4 (Web Text))

Max Activating Token Index: 644