Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.6092. Min Act: -0.1700
Data Index: 5499349 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.4842. Min Act: -0.1700
Data Index: 7303642 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.2342. Min Act: -0.1700
Data Index: 5727935 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.2342. Min Act: -0.1700
Data Index: 2823537 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.1717. Min Act: -0.1700
Data Index: 4168566 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.1092. Min Act: -0.1700
Data Index: 590786 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.1092. Min Act: -0.1700
Data Index: 2239861 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6092. Min Range: -9.6092
Max Act: 9.0467. Min Act: -0.1700
Data Index: 6235076 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.9842. Min Act: -0.1700
Data Index: 7918664 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.9217. Min Act: -0.1700
Data Index: 5760613 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.8592. Min Act: -0.1700
Data Index: 3628853 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.7967. Min Act: -0.1700
Data Index: 4986698 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.8592. Min Act: -0.1700
Data Index: 4810702 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.9217. Min Act: -0.1700
Data Index: 4304066 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.8592. Min Act: -0.1700
Data Index: 1708095 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.8592. Min Act: -0.1700
Data Index: 1514501 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.8592. Min Act: -0.1700
Data Index: 4168567 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.9217. Min Act: -0.1700
Data Index: 8644811 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.7967. Min Act: -0.1700
Data Index: 6398650 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6092. Min Range: -9.6092
Max Act: 8.7967. Min Act: -0.1700
Data Index: 2078236 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19