Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.7880. Min Act: -0.1700
Data Index: 7323563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.7255. Min Act: -0.1700
Data Index: 5132542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.6630. Min Act: -0.1700
Data Index: 5858950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.5380. Min Act: -0.1700
Data Index: 2922230 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.5380. Min Act: -0.1700
Data Index: 7254745 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.5380. Min Act: -0.1700
Data Index: 7280189 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4755. Min Act: -0.1700
Data Index: 670377 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4755. Min Act: -0.1700
Data Index: 1066053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 7044004 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 3427943 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 424007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 3207930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 800006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 875420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 890376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 3732447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 1681350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 1597468 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 2826901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.7880. Min Range: -14.7880
Max Act: 14.4130. Min Act: -0.1700
Data Index: 9918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19