Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2725. Min Range: -5.2725
Max Act: 5.2725. Min Act: -0.1700
Data Index: 895426 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2725. Min Range: -5.2725
Max Act: 5.0537. Min Act: -0.1700
Data Index: 6390227 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2725. Min Range: -5.2725
Max Act: 5.0225. Min Act: -0.1700
Data Index: 2559162 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.9912. Min Act: -0.1700
Data Index: 1762138 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.9600. Min Act: -0.1700
Data Index: 5466546 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.9600. Min Act: -0.1700
Data Index: 1887000 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.9600. Min Act: -0.1700
Data Index: 5392099 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.9287. Min Act: -0.1700
Data Index: 2373149 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8662. Min Act: -0.1700
Data Index: 7278335 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8975. Min Act: -0.1700
Data Index: 572444 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8975. Min Act: -0.1700
Data Index: 3194766 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8975. Min Act: -0.1700
Data Index: 4714093 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8975. Min Act: -0.1700
Data Index: 3863857 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8975. Min Act: -0.1700
Data Index: 880708 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8975. Min Act: -0.1700
Data Index: 7687012 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8662. Min Act: -0.1700
Data Index: 2148006 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8662. Min Act: -0.1700
Data Index: 597532 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8662. Min Act: -0.1700
Data Index: 1637440 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8037. Min Act: -0.1700
Data Index: 6173698 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2725. Min Range: -5.2725
Max Act: 4.8350. Min Act: -0.1700
Data Index: 8818442 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19