Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5774. Min Range: -8.5774
Max Act: 8.5774. Min Act: -0.1700
Data Index: 1249871 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5774. Min Range: -8.5774
Max Act: 8.0149. Min Act: -0.1700
Data Index: 2046234 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.5462. Min Act: -0.1700
Data Index: 6020591 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.4837. Min Act: -0.1700
Data Index: 6512115 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.4212. Min Act: -0.1700
Data Index: 1980938 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.4212. Min Act: -0.1700
Data Index: 5361396 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.3587. Min Act: -0.1700
Data Index: 4566419 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.3899. Min Act: -0.1700
Data Index: 3510984 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2962. Min Act: -0.1700
Data Index: 4090661 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2962. Min Act: -0.1700
Data Index: 2652827 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2962. Min Act: -0.1700
Data Index: 4786710 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2649. Min Act: -0.1700
Data Index: 6968937 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2337. Min Act: -0.1700
Data Index: 100359 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2024. Min Act: -0.1700
Data Index: 2221781 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.1712. Min Act: -0.1700
Data Index: 7228873 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.1712. Min Act: -0.1700
Data Index: 2221780 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.1399. Min Act: -0.1700
Data Index: 4116609 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.1712. Min Act: -0.1700
Data Index: 7389870 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.2024. Min Act: -0.1700
Data Index: 4722804 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5774. Min Range: -8.5774
Max Act: 7.1087. Min Act: -0.1700
Data Index: 6067325 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19