Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0841. Min Range: -4.0841
Max Act: 4.0841. Min Act: -0.1700
Data Index: 6415643 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0841. Min Range: -4.0841
Max Act: 4.0529. Min Act: -0.1700
Data Index: 1926690 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0841. Min Range: -4.0841
Max Act: 4.0216. Min Act: -0.1700
Data Index: 6728324 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9904. Min Act: -0.1700
Data Index: 544237 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9904. Min Act: -0.1700
Data Index: 6887052 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9904. Min Act: -0.1700
Data Index: 1729631 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9278. Min Act: -0.1700
Data Index: 6185656 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9278. Min Act: -0.1700
Data Index: 670546 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9278. Min Act: -0.1700
Data Index: 1874873 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9278. Min Act: -0.1700
Data Index: 3333617 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8966. Min Act: -0.1700
Data Index: 4620692 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8966. Min Act: -0.1700
Data Index: 7016715 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.9278. Min Act: -0.1700
Data Index: 5546693 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8966. Min Act: -0.1700
Data Index: 7507872 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8966. Min Act: -0.1700
Data Index: 8080273 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8653. Min Act: -0.1700
Data Index: 5047911 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8653. Min Act: -0.1700
Data Index: 4863116 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8653. Min Act: -0.1700
Data Index: 4194704 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8653. Min Act: -0.1700
Data Index: 7429895 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0841. Min Range: -4.0841
Max Act: 3.8340. Min Act: -0.1700
Data Index: 740029 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19