Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4862. Min Range: -8.4862
Max Act: 8.4862. Min Act: -0.1700
Data Index: 8666294 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4862. Min Range: -8.4862
Max Act: 8.4237. Min Act: -0.1700
Data Index: 2149369 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4862. Min Range: -8.4862
Max Act: 8.0799. Min Act: -0.1700
Data Index: 4386810 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4862. Min Range: -8.4862
Max Act: 8.0487. Min Act: -0.1700
Data Index: 1091306 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9862. Min Act: -0.1700
Data Index: 6133904 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9549. Min Act: -0.1700
Data Index: 1734700 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9549. Min Act: -0.1700
Data Index: 3677063 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 2912482 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9549. Min Act: -0.1700
Data Index: 3844598 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 712298 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 3497978 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 959011 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.8924. Min Act: -0.1700
Data Index: 5690133 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 1760009 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 6201831 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.9237. Min Act: -0.1700
Data Index: 4445653 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.7674. Min Act: -0.1700
Data Index: 2878434 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.7674. Min Act: -0.1700
Data Index: 3936823 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.7362. Min Act: -0.1700
Data Index: 1563364 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4862. Min Range: -8.4862
Max Act: 7.7362. Min Act: -0.1700
Data Index: 7244733 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19