Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1491 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0979. Min Range: -5.0979
Max Act: 5.0979. Min Act: -0.1700
Data Index: 4431584 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.9417. Min Act: -0.1700
Data Index: 5645676 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.7854. Min Act: -0.1700
Data Index: 5046018 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.7229. Min Act: -0.1700
Data Index: 4166634 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.7229. Min Act: -0.1700
Data Index: 5720898 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.7229. Min Act: -0.1700
Data Index: 4668686 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6917. Min Act: -0.1700
Data Index: 4668687 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6604. Min Act: -0.1700
Data Index: 5720897 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6917. Min Act: -0.1700
Data Index: 3694459 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6604. Min Act: -0.1700
Data Index: 249005 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6604. Min Act: -0.1700
Data Index: 6458009 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8590629 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5979. Min Act: -0.1700
Data Index: 2459828 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5979. Min Act: -0.1700
Data Index: 5119525 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5979. Min Act: -0.1700
Data Index: 5914774 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5667. Min Act: -0.1700
Data Index: 7097301 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5667. Min Act: -0.1700
Data Index: 1897164 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5667. Min Act: -0.1700
Data Index: 7832387 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5667. Min Act: -0.1700
Data Index: 1500432 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0979. Min Range: -5.0979
Max Act: 4.5667. Min Act: -0.1700
Data Index: 8619814 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19