Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6262 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.9606. Min Act: -0.1700
Data Index: 7062170 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.9918. Min Act: -0.1700
Data Index: 4582654 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.9293. Min Act: -0.1700
Data Index: 6167246 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8668. Min Act: -0.1700
Data Index: 5897772 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8668. Min Act: -0.1700
Data Index: 6325725 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8668. Min Act: -0.1700
Data Index: 1282574 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8668. Min Act: -0.1700
Data Index: 8041059 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8981. Min Act: -0.1700
Data Index: 2939760 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8668. Min Act: -0.1698
Data Index: 1052000 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8356. Min Act: -0.1700
Data Index: 1966649 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8356. Min Act: -0.1700
Data Index: 1074853 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8043. Min Act: -0.1700
Data Index: 5381552 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8043. Min Act: -0.1700
Data Index: 5673752 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8043. Min Act: -0.1697
Data Index: 189429 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8043. Min Act: -0.1700
Data Index: 463310 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.7731. Min Act: -0.1700
Data Index: 4703386 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.7731. Min Act: -0.1700
Data Index: 7892784 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.7731. Min Act: -0.1700
Data Index: 7588426 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.8043. Min Act: -0.1700
Data Index: 4150787 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9918. Min Range: -6.9918
Max Act: 6.7418. Min Act: -0.1700
Data Index: 1557556 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19