Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.6895. Min Act: -0.1700
Data Index: 5105452 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.5020. Min Act: -0.1700
Data Index: 4295906 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.3145. Min Act: -0.1700
Data Index: 5932650 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.2832. Min Act: -0.1700
Data Index: 735184 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.2520. Min Act: -0.1700
Data Index: 6375683 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.2520. Min Act: -0.1700
Data Index: 8395800 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.0957. Min Act: -0.1700
Data Index: 7215155 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6895. Min Range: -6.6895
Max Act: 6.0332. Min Act: -0.1700
Data Index: 6571614 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.9707. Min Act: -0.1700
Data Index: 5985777 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.9082. Min Act: -0.1700
Data Index: 4577596 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.9082. Min Act: -0.1700
Data Index: 651231 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.9082. Min Act: -0.1700
Data Index: 8123540 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8457. Min Act: -0.1700
Data Index: 5937509 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8145. Min Act: -0.1700
Data Index: 5148050 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8457. Min Act: -0.1700
Data Index: 3922321 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8457. Min Act: -0.1700
Data Index: 7872505 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2112746 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8145. Min Act: -0.1700
Data Index: 1791277 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8145. Min Act: -0.1700
Data Index: 4986163 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6895. Min Range: -6.6895
Max Act: 5.8145. Min Act: -0.1700
Data Index: 3429197 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19