Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.7988. Min Act: -0.1700
Data Index: 2898626 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.6113. Min Act: -0.1700
Data Index: 7505017 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.5488. Min Act: -0.1700
Data Index: 7727206 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.4863. Min Act: -0.1700
Data Index: 2590005 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.3613. Min Act: -0.1700
Data Index: 2092616 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.4238. Min Act: -0.1700
Data Index: 7027095 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.4238. Min Act: -0.1700
Data Index: 6443642 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.4238. Min Act: -0.1700
Data Index: 2087578 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.4238. Min Act: -0.1700
Data Index: 2787362 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.4238. Min Act: -0.1700
Data Index: 5241413 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.3613. Min Act: -0.1700
Data Index: 5694009 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.3613. Min Act: -0.1700
Data Index: 290280 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.3613. Min Act: -0.1700
Data Index: 6887053 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.2988. Min Act: -0.1700
Data Index: 251414 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.2363. Min Act: -0.1700
Data Index: 7650956 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.2363. Min Act: -0.1700
Data Index: 2339207 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.2363. Min Act: -0.1700
Data Index: 6775761 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.2363. Min Act: -0.1700
Data Index: 4259194 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.1738. Min Act: -0.1700
Data Index: 2904932 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7988. Min Range: -8.7988
Max Act: 8.1738. Min Act: -0.1700
Data Index: 3107683 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19