Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2185 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.7061. Min Act: -0.1700
Data Index: 4392445 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 732944 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 678437 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.5186. Min Act: -0.1700
Data Index: 123584 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.4249. Min Act: -0.1700
Data Index: 810043 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2999. Min Act: -0.1700
Data Index: 4296799 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2374. Min Act: -0.1700
Data Index: 6662813 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 664749 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 4794455 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 1411633 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 375662 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.2061. Min Act: -0.1700
Data Index: 338335 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.1749. Min Act: -0.1700
Data Index: 882071 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.1749. Min Act: -0.1700
Data Index: 8003649 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.1436. Min Act: -0.1700
Data Index: 1201918 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.1124. Min Act: -0.1700
Data Index: 6836489 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.1124. Min Act: -0.1700
Data Index: 6925460 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.0811. Min Act: -0.1700
Data Index: 1088563 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.0811. Min Act: -0.1700
Data Index: 4496860 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7061. Min Range: -6.7061
Max Act: 6.0499. Min Act: -0.1700
Data Index: 2529012 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19