Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4519 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.3867. Min Act: -0.1700
Data Index: 3224727 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.1679. Min Act: -0.1700
Data Index: 1785186 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.1679. Min Act: -0.1700
Data Index: 640662 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.1367. Min Act: -0.1700
Data Index: 7044506 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.1054. Min Act: -0.1700
Data Index: 8254622 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.1054. Min Act: -0.1700
Data Index: 1410903 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.0742. Min Act: -0.1700
Data Index: 8762942 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.0429. Min Act: -0.1700
Data Index: 8482464 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3867. Min Range: -5.3867
Max Act: 5.0429. Min Act: -0.1700
Data Index: 1410902 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9804. Min Act: -0.1700
Data Index: 4246311 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9804. Min Act: -0.1700
Data Index: 4269574 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9804. Min Act: -0.1700
Data Index: 4488427 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9804. Min Act: -0.1700
Data Index: 2014546 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9804. Min Act: -0.1700
Data Index: 3297849 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9492. Min Act: -0.1700
Data Index: 1410901 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9492. Min Act: -0.1700
Data Index: 2915409 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9492. Min Act: -0.1700
Data Index: 6173889 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9179. Min Act: -0.1700
Data Index: 2942177 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9179. Min Act: -0.1700
Data Index: 7921685 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3867. Min Range: -5.3867
Max Act: 4.9179. Min Act: -0.1700
Data Index: 4488429 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19