Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1747. Min Range: -6.1747
Max Act: 6.1747. Min Act: -0.1700
Data Index: 8806763 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.8310. Min Act: -0.1700
Data Index: 5196946 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.7997. Min Act: -0.1700
Data Index: 3427943 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.7685. Min Act: -0.1700
Data Index: 916420 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.7372. Min Act: -0.1700
Data Index: 6137977 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.7372. Min Act: -0.1700
Data Index: 5160103 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6747. Min Act: -0.1700
Data Index: 8690452 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.7060. Min Act: -0.1700
Data Index: 7771376 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6747. Min Act: -0.1700
Data Index: 4695819 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6747. Min Act: -0.1700
Data Index: 716281 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6747. Min Act: -0.1700
Data Index: 1607274 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6747. Min Act: -0.1700
Data Index: 4508770 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6435. Min Act: -0.1700
Data Index: 5669668 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6435. Min Act: -0.1700
Data Index: 3381577 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6122. Min Act: -0.1700
Data Index: 4271167 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.6122. Min Act: -0.1700
Data Index: 4136411 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2674049 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2202241 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.5497. Min Act: -0.1700
Data Index: 5940287 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1747. Min Range: -6.1747
Max Act: 5.5497. Min Act: -0.1700
Data Index: 2012968 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19