Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4505 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.9014. Min Act: -0.1700
Data Index: 4866974 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.9014. Min Act: -0.1700
Data Index: 8380319 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.8389. Min Act: -0.1700
Data Index: 5128512 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.8076. Min Act: -0.1700
Data Index: 499308 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.8076. Min Act: -0.1700
Data Index: 3075506 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.7764. Min Act: -0.1700
Data Index: 512639 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.7451. Min Act: -0.1700
Data Index: 5012567 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.7139. Min Act: -0.1700
Data Index: 6142313 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.7139. Min Act: -0.1700
Data Index: 861031 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.6826. Min Act: -0.1700
Data Index: 4952298 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.6826. Min Act: -0.1700
Data Index: 1447905 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.6514. Min Act: -0.1700
Data Index: 7769179 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.6514. Min Act: -0.1700
Data Index: 1698298 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.6201. Min Act: -0.1700
Data Index: 6617903 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.6201. Min Act: -0.1700
Data Index: 8292273 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.5889. Min Act: -0.1700
Data Index: 6780629 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.5889. Min Act: -0.1700
Data Index: 4789932 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.5576. Min Act: -0.1700
Data Index: 5804046 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.5576. Min Act: -0.1700
Data Index: 3922130 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9014. Min Range: -4.9014
Max Act: 4.5576. Min Act: -0.1700
Data Index: 5930675 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19