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

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

Neuron 974 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: 3.1664. Min Range: -3.1664

Max Act: 3.1507. Min Act: -0.1700

Data Index: 1544463 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.1664. Min Act: -0.1700

Data Index: 195331 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.1349. Min Act: -0.1700

Data Index: 1122284 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0876. Min Act: -0.1700

Data Index: 464260 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.1034. Min Act: -0.1700

Data Index: 1215679 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.1192. Min Act: -0.1700

Data Index: 1345468 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0876. Min Act: -0.1700

Data Index: 616950 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0876. Min Act: -0.1700

Data Index: 397748 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.1034. Min Act: -0.1700

Data Index: 184661 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0876. Min Act: -0.1700

Data Index: 709114 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1134851 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0718. Min Act: -0.1700

Data Index: 479200 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0718. Min Act: -0.1700

Data Index: 468867 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0718. Min Act: -0.1700

Data Index: 92939 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0561. Min Act: -0.1700

Data Index: 986510 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0561. Min Act: -0.1700

Data Index: 494995 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0561. Min Act: -0.1700

Data Index: 305334 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0561. Min Act: -0.1700

Data Index: 678322 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0403. Min Act: -0.1700

Data Index: 72715 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.1664. Min Range: -3.1664

Max Act: 3.0718. Min Act: -0.1700

Data Index: 482027 (C4 (Web Text))

Max Activating Token Index: 186