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

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

Neuron 351 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.6252. Min Act: -0.1700

Data Index: 623429 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3752. Min Act: -0.1700

Data Index: 1322363 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3752. Min Act: -0.1700

Data Index: 1074103 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.4377. Min Act: -0.1700

Data Index: 302118 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3752. Min Act: -0.1700

Data Index: 115404 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1700

Data Index: 1097915 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3752. Min Act: -0.1700

Data Index: 1348836 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1700

Data Index: 470741 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3752. Min Act: -0.1700

Data Index: 168610 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1699

Data Index: 662911 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1700

Data Index: 1045529 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1700

Data Index: 929256 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3127. Min Act: -0.1700

Data Index: 286880 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1700

Data Index: 49763 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3127. Min Act: -0.1700

Data Index: 184403 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3127. Min Act: -0.1700

Data Index: 1076345 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3127. Min Act: -0.1700

Data Index: 129960 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.3440. Min Act: -0.1700

Data Index: 418403 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.2502. Min Act: -0.1700

Data Index: 603664 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 5.6252. Min Range: -5.6252

Max Act: 5.2502. Min Act: -0.1700

Data Index: 673147 (C4 (Web Text))

Max Activating Token Index: 664