Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1914. Min Range: -7.1914
Max Act: 7.1914. Min Act: -0.1700
Data Index: 7057658 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.9726. Min Act: -0.1700
Data Index: 2061351 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.9414. Min Act: -0.1700
Data Index: 1351562 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8789. Min Act: -0.1700
Data Index: 6265292 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8789. Min Act: -0.1700
Data Index: 3835358 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8789. Min Act: -0.1700
Data Index: 1565491 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8789. Min Act: -0.1700
Data Index: 3938945 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8476. Min Act: -0.1700
Data Index: 5578324 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8164. Min Act: -0.1700
Data Index: 7705538 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8164. Min Act: -0.1700
Data Index: 3071952 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7851. Min Act: -0.1700
Data Index: 4152941 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7226. Min Act: -0.1700
Data Index: 6904951 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7226. Min Act: -0.1700
Data Index: 2002446 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7226. Min Act: -0.1700
Data Index: 926312 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.6914. Min Act: -0.1700
Data Index: 3914387 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5827634 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5732214 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7226. Min Act: -0.1700
Data Index: 6444046 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.6914. Min Act: -0.1700
Data Index: 1461835 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.6601. Min Act: -0.1700
Data Index: 1173265 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19