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

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

Neuron 1964 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: 3.3080. Min Range: -3.3080

Max Act: 3.3080. Min Act: -0.1700

Data Index: 120735 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.2452. Min Act: -0.1700

Data Index: 78705 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.1822. Min Act: -0.1700

Data Index: 87669 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.1665. Min Act: -0.1700

Data Index: 158151 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.1035. Min Act: -0.1700

Data Index: 747237 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.1350. Min Act: -0.1700

Data Index: 1279353 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.1035. Min Act: -0.1700

Data Index: 995449 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0877. Min Act: -0.1700

Data Index: 240102 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0719. Min Act: -0.1700

Data Index: 980494 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0877. Min Act: -0.1700

Data Index: 689514 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0719. Min Act: -0.1700

Data Index: 740063 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0562. Min Act: -0.1700

Data Index: 825769 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.3080. Min Range: -3.3080

Max Act: 2.9930. Min Act: -0.1700

Data Index: 1317780 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0088. Min Act: -0.1700

Data Index: 1300487 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0562. Min Act: -0.1700

Data Index: 510688 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0404. Min Act: -0.1700

Data Index: 432229 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0246. Min Act: -0.1700

Data Index: 1342905 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0088. Min Act: -0.1700

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 3.3080. Min Range: -3.3080

Max Act: 2.9455. Min Act: -0.1700

Data Index: 1085306 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 3.3080. Min Range: -3.3080

Max Act: 3.0088. Min Act: -0.1700

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 959