Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.8309. Min Act: -0.1700
Data Index: 3567782 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.7059. Min Act: -0.1700
Data Index: 5445986 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3934. Min Act: -0.1700
Data Index: 2075704 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3934. Min Act: -0.1700
Data Index: 8070950 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3934. Min Act: -0.1700
Data Index: 3178265 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3309. Min Act: -0.1700
Data Index: 2926599 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3309. Min Act: -0.1700
Data Index: 426330 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3309. Min Act: -0.1700
Data Index: 5685432 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3309. Min Act: -0.1700
Data Index: 628949 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.3309. Min Act: -0.1700
Data Index: 1542988 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.2059. Min Act: -0.1700
Data Index: 7704265 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.2059. Min Act: -0.1700
Data Index: 1192047 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.1434. Min Act: -0.1700
Data Index: 4971355 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.1122. Min Act: -0.1700
Data Index: 194840 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.0809. Min Act: -0.1700
Data Index: 1616814 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.0809. Min Act: -0.1700
Data Index: 5932553 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.0184. Min Act: -0.1700
Data Index: 6794346 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.0184. Min Act: -0.1700
Data Index: 643044 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.0184. Min Act: -0.1700
Data Index: 1593568 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8309. Min Range: -8.8309
Max Act: 8.0184. Min Act: -0.1700
Data Index: 6108086 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19