Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6298. Min Range: -6.6298
Max Act: 6.6298. Min Act: -0.1700
Data Index: 5420940 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6298. Min Range: -6.6298
Max Act: 6.4423. Min Act: -0.1700
Data Index: 4190 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6298. Min Range: -6.6298
Max Act: 6.1611. Min Act: -0.1700
Data Index: 2796003 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6298. Min Range: -6.6298
Max Act: 6.1611. Min Act: -0.1700
Data Index: 5275850 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6298. Min Range: -6.6298
Max Act: 6.0986. Min Act: -0.1700
Data Index: 1900405 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6298. Min Range: -6.6298
Max Act: 6.0048. Min Act: -0.1700
Data Index: 2957567 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.9736. Min Act: -0.1700
Data Index: 3798239 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.9736. Min Act: -0.1700
Data Index: 5825988 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.9423. Min Act: -0.1700
Data Index: 2503885 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.9736. Min Act: -0.1700
Data Index: 2904096 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.9111. Min Act: -0.1700
Data Index: 1961940 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.9111. Min Act: -0.1700
Data Index: 3715469 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8798. Min Act: -0.1700
Data Index: 4670471 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8798. Min Act: -0.1700
Data Index: 6465101 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8486. Min Act: -0.1700
Data Index: 4636791 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8486. Min Act: -0.1700
Data Index: 4177715 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1966368 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8486. Min Act: -0.1700
Data Index: 23486 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.7861. Min Act: -0.1700
Data Index: 5359647 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6298. Min Range: -6.6298
Max Act: 5.8173. Min Act: -0.1700
Data Index: 5003940 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19