Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.2002. Min Act: -0.1700
Data Index: 5228581 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.2002. Min Act: -0.1700
Data Index: 3962680 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.1377. Min Act: -0.1700
Data Index: 7779152 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.1377. Min Act: -0.1700
Data Index: 6022651 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.1377. Min Act: -0.1700
Data Index: 4767979 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.1064. Min Act: -0.1700
Data Index: 8819875 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0752. Min Act: -0.1700
Data Index: 6904164 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.1064. Min Act: -0.1700
Data Index: 5202980 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0752. Min Act: -0.1700
Data Index: 8443964 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0752. Min Act: -0.1700
Data Index: 6811769 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0127. Min Act: -0.1700
Data Index: 1149392 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0127. Min Act: -0.1700
Data Index: 6789368 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0127. Min Act: -0.1700
Data Index: 230003 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0127. Min Act: -0.1700
Data Index: 61825 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9814. Min Act: -0.1700
Data Index: 2737412 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0127. Min Act: -0.1700
Data Index: 6777611 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9814. Min Act: -0.1700
Data Index: 4211486 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9502. Min Act: -0.1700
Data Index: 5900991 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9189. Min Act: -0.1700
Data Index: 6991622 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9189. Min Act: -0.1700
Data Index: 4485342 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19