Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1126. Min Range: -8.1126
Max Act: 8.1126. Min Act: -0.1700
Data Index: 8760341 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1126. Min Range: -8.1126
Max Act: 8.0188. Min Act: -0.1700
Data Index: 5755476 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.8938. Min Act: -0.1700
Data Index: 4918683 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.8938. Min Act: -0.1700
Data Index: 4918684 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.9251. Min Act: -0.1700
Data Index: 5755480 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.8313. Min Act: -0.1700
Data Index: 5755479 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.8001. Min Act: -0.1700
Data Index: 7998766 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.7688. Min Act: -0.1700
Data Index: 2331620 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.7688. Min Act: -0.1700
Data Index: 5755481 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.7063. Min Act: -0.1700
Data Index: 9836 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.7376. Min Act: -0.1700
Data Index: 5425896 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.6438. Min Act: -0.1700
Data Index: 1145981 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.6438. Min Act: -0.1700
Data Index: 5755483 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.6438. Min Act: -0.1700
Data Index: 6258492 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.6126. Min Act: -0.1700
Data Index: 2156733 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.5813. Min Act: -0.1700
Data Index: 6301669 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.5501. Min Act: -0.1700
Data Index: 2829727 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.5188. Min Act: -0.1700
Data Index: 8721599 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.5501. Min Act: -0.1700
Data Index: 5755471 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1126. Min Range: -8.1126
Max Act: 7.5188. Min Act: -0.1700
Data Index: 1461508 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19