Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.7890. Min Act: -0.1700

Data Index: 1629114 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.6015. Min Act: -0.1700

Data Index: 1431367 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5390. Min Act: -0.1700

Data Index: 1586910 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5702. Min Act: -0.1700

Data Index: 1422164 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5702. Min Act: -0.1700

Data Index: 1498092 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5390. Min Act: -0.1700

Data Index: 1389179 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5077. Min Act: -0.1700

Data Index: 1574215 (Python Code)

Max Activating Token Index: 569

Text #7

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5702. Min Act: -0.1700

Data Index: 1381214 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5702. Min Act: -0.1700

Data Index: 1369883 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5077. Min Act: -0.1700

Data Index: 1495664 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5077. Min Act: -0.1700

Data Index: 1410896 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.4765. Min Act: -0.1700

Data Index: 1574636 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5077. Min Act: -0.1700

Data Index: 1384043 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5702. Min Act: -0.1700

Data Index: 1631326 (Python Code)

Max Activating Token Index: 655

Text #14

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5077. Min Act: -0.1700

Data Index: 1371423 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5390. Min Act: -0.1700

Data Index: 1570018 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.4765. Min Act: -0.1699

Data Index: 1538108 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.5702. Min Act: -0.1700

Data Index: 1534279 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.4765. Min Act: -0.1700

Data Index: 1623751 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 5.7890. Min Range: -5.7890

Max Act: 5.4765. Min Act: -0.1700

Data Index: 1614117 (Python Code)

Max Activating Token Index: 226