Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.8741. Min Act: -0.1700
Data Index: 4199716 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.7491. Min Act: -0.1700
Data Index: 7299478 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.6554. Min Act: -0.1700
Data Index: 5722558 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5929. Min Act: -0.1700
Data Index: 688934 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5929. Min Act: -0.1700
Data Index: 7152326 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5616. Min Act: -0.1700
Data Index: 5875564 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5616. Min Act: -0.1700
Data Index: 6520313 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5304. Min Act: -0.1700
Data Index: 8575571 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4991. Min Act: -0.1700
Data Index: 5633660 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4366. Min Act: -0.1700
Data Index: 3860959 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4366. Min Act: -0.1700
Data Index: 2778826 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4054. Min Act: -0.1700
Data Index: 3595791 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4054. Min Act: -0.1700
Data Index: 8110812 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3741. Min Act: -0.1700
Data Index: 2588573 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3741. Min Act: -0.1700
Data Index: 4598189 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3429. Min Act: -0.1700
Data Index: 5190025 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3429. Min Act: -0.1700
Data Index: 5120408 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3429. Min Act: -0.1700
Data Index: 2970482 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3116. Min Act: -0.1700
Data Index: 7056236 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.3116. Min Act: -0.1700
Data Index: 3533677 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19