Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0775. Min Range: -9.0775
Max Act: 9.0775. Min Act: -0.1700
Data Index: 2513975 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.5775. Min Act: -0.1700
Data Index: 7172777 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.5775. Min Act: -0.1700
Data Index: 2273660 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.3275. Min Act: -0.1700
Data Index: 7085793 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.3275. Min Act: -0.1700
Data Index: 5549220 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.2025. Min Act: -0.1700
Data Index: 4155893 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.0462. Min Act: -0.1700
Data Index: 993213 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0775. Min Range: -9.0775
Max Act: 8.0150. Min Act: -0.1700
Data Index: 5534747 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.9525. Min Act: -0.1700
Data Index: 6028239 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.8900. Min Act: -0.1700
Data Index: 5643758 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.6400. Min Act: -0.1700
Data Index: 6368964 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.6712. Min Act: -0.1700
Data Index: 680932 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.6712. Min Act: -0.1700
Data Index: 1609085 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.6400. Min Act: -0.1700
Data Index: 2029015 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.5775. Min Act: -0.1700
Data Index: 5643756 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.5775. Min Act: -0.1700
Data Index: 5643759 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.5462. Min Act: -0.1700
Data Index: 2531618 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.5150. Min Act: -0.1700
Data Index: 6541302 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.5150. Min Act: -0.1700
Data Index: 2472169 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0775. Min Range: -9.0775
Max Act: 7.5462. Min Act: -0.1700
Data Index: 151921 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19