Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.1718. Min Act: -0.1700
Data Index: 1788462 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.1406. Min Act: -0.1700
Data Index: 3005035 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.0781. Min Act: -0.1700
Data Index: 8007288 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.0781. Min Act: -0.1700
Data Index: 7413405 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.1093. Min Act: -0.1700
Data Index: 7849183 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.0781. Min Act: -0.1700
Data Index: 6516916 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.0468. Min Act: -0.1700
Data Index: 7411654 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1718. Min Range: -5.1718
Max Act: 5.0156. Min Act: -0.1700
Data Index: 1749749 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9843. Min Act: -0.1700
Data Index: 1423561 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9843. Min Act: -0.1700
Data Index: 8686588 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9531. Min Act: -0.1700
Data Index: 546564 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9531. Min Act: -0.1700
Data Index: 7510311 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.8906. Min Act: -0.1700
Data Index: 1643774 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9218. Min Act: -0.1700
Data Index: 6565412 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9218. Min Act: -0.1700
Data Index: 8787801 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.9218. Min Act: -0.1700
Data Index: 2000701 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.8906. Min Act: -0.1700
Data Index: 4575139 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.8906. Min Act: -0.1700
Data Index: 4054370 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.8593. Min Act: -0.1700
Data Index: 6545181 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1718. Min Range: -5.1718
Max Act: 4.8593. Min Act: -0.1700
Data Index: 46754 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19