Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.6328. Min Act: -0.1700
Data Index: 679644 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.5391. Min Act: -0.1700
Data Index: 6786963 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.4766. Min Act: -0.1700
Data Index: 7202846 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.4453. Min Act: -0.1700
Data Index: 8483439 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.4141. Min Act: -0.1700
Data Index: 6646993 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.3516. Min Act: -0.1700
Data Index: 3080703 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.3516. Min Act: -0.1698
Data Index: 1566619 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.3516. Min Act: -0.1700
Data Index: 8729609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.3516. Min Act: -0.1700
Data Index: 7413831 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.2891. Min Act: -0.1700
Data Index: 3314471 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1953. Min Act: -0.1700
Data Index: 7989238 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.2266. Min Act: -0.1700
Data Index: 3841860 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1953. Min Act: -0.1699
Data Index: 2927680 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1953. Min Act: -0.1700
Data Index: 1173122 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1953. Min Act: -0.1700
Data Index: 6797183 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1641. Min Act: -0.1700
Data Index: 3426720 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1641. Min Act: -0.1700
Data Index: 8561360 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1641. Min Act: -0.1700
Data Index: 7836612 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1016. Min Act: -0.1700
Data Index: 1590018 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6328. Min Range: -5.6328
Max Act: 5.1328. Min Act: -0.1700
Data Index: 4004802 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19