Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4826. Min Range: -8.4826
Max Act: 8.4826. Min Act: -0.1700
Data Index: 4018941 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4826. Min Range: -8.4826
Max Act: 8.3576. Min Act: -0.1700
Data Index: 6180937 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4826. Min Range: -8.4826
Max Act: 8.1701. Min Act: -0.1700
Data Index: 4089578 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.9826. Min Act: -0.1700
Data Index: 1958880 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.9201. Min Act: -0.1700
Data Index: 2311981 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.9201. Min Act: -0.1700
Data Index: 498351 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.8576. Min Act: -0.1700
Data Index: 8056576 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.8576. Min Act: -0.1700
Data Index: 3029609 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.8576. Min Act: -0.1700
Data Index: 3964024 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.7951. Min Act: -0.1700
Data Index: 1871500 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.7326. Min Act: -0.1700
Data Index: 2870227 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.7326. Min Act: -0.1700
Data Index: 8486702 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.7326. Min Act: -0.1700
Data Index: 3178085 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.7326. Min Act: -0.1700
Data Index: 7271372 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.6701. Min Act: -0.1700
Data Index: 6561384 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.6701. Min Act: -0.1700
Data Index: 4092029 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.6701. Min Act: -0.1700
Data Index: 1685763 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.6701. Min Act: -0.1700
Data Index: 7396299 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.6076. Min Act: -0.1700
Data Index: 6109140 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4826. Min Range: -8.4826
Max Act: 7.6076. Min Act: -0.1700
Data Index: 8642110 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19