Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2648 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.6404. Min Act: -0.1700
Data Index: 3326567 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.6091. Min Act: -0.1700
Data Index: 2192791 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.3904. Min Act: -0.1700
Data Index: 7013840 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.3279. Min Act: -0.1700
Data Index: 7189266 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.3279. Min Act: -0.1700
Data Index: 6856986 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.2341. Min Act: -0.1700
Data Index: 3929663 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.2341. Min Act: -0.1700
Data Index: 7103993 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.1091. Min Act: -0.1700
Data Index: 732782 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.1091. Min Act: -0.1700
Data Index: 3400418 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.0779. Min Act: -0.1700
Data Index: 2448237 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.0779. Min Act: -0.1700
Data Index: 8502194 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.0779. Min Act: -0.1700
Data Index: 7091399 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.0466. Min Act: -0.1700
Data Index: 3738976 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6404. Min Range: -7.6404
Max Act: 7.0466. Min Act: -0.1700
Data Index: 3662973 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6404. Min Range: -7.6404
Max Act: 6.9529. Min Act: -0.1700
Data Index: 5650737 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6404. Min Range: -7.6404
Max Act: 6.9841. Min Act: -0.1700
Data Index: 3343170 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6404. Min Range: -7.6404
Max Act: 6.9216. Min Act: -0.1700
Data Index: 875839 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6404. Min Range: -7.6404
Max Act: 6.8904. Min Act: -0.1700
Data Index: 5842058 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6404. Min Range: -7.6404
Max Act: 6.8591. Min Act: -0.1700
Data Index: 1851721 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6404. Min Range: -7.6404
Max Act: 6.8904. Min Act: -0.1700
Data Index: 3620964 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19