Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9797. Min Act: -0.1700
Data Index: 3336349 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 3694124 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 7381057 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 1165851 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 7461705 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 8753867 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 2844743 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 2052375 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 2175966 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.7922. Min Act: -0.1700
Data Index: 2376096 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 915466 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 902406 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 2354527 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 2275587 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 2074635 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1896743 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1830220 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1735908 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1517247 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9797. Min Range: -7.9797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 400377 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19