Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.4509. Min Act: -0.1700
Data Index: 7580544 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.3259. Min Act: -0.1700
Data Index: 314492 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.2947. Min Act: -0.1700
Data Index: 4689772 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.2322. Min Act: -0.1700
Data Index: 1495686 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.2009. Min Act: -0.1700
Data Index: 2562011 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.1697. Min Act: -0.1700
Data Index: 6931846 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.1072. Min Act: -0.1700
Data Index: 7628590 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.1384. Min Act: -0.1700
Data Index: 1328259 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.1072. Min Act: -0.1700
Data Index: 3535144 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.0759. Min Act: -0.1700
Data Index: 3882613 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.0759. Min Act: -0.1700
Data Index: 4769093 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.0447. Min Act: -0.1700
Data Index: 4332258 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4509. Min Range: -5.4509
Max Act: 5.0759. Min Act: -0.1700
Data Index: 8035131 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.9822. Min Act: -0.1700
Data Index: 555369 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.9509. Min Act: -0.1700
Data Index: 710217 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.8884. Min Act: -0.1700
Data Index: 5091452 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.9197. Min Act: -0.1700
Data Index: 7461983 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.9197. Min Act: -0.1700
Data Index: 5972947 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.8572. Min Act: -0.1700
Data Index: 3369199 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4509. Min Range: -5.4509
Max Act: 4.8572. Min Act: -0.1700
Data Index: 5778348 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19