Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.5065. Min Act: -0.1700
Data Index: 3555206 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.1940. Min Act: -0.1700
Data Index: 93279 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.1940. Min Act: -0.1700
Data Index: 6103807 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.1940. Min Act: -0.1700
Data Index: 7656422 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.1315. Min Act: -0.1700
Data Index: 8044372 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.1315. Min Act: -0.1700
Data Index: 6715425 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.0690. Min Act: -0.1700
Data Index: 6043765 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.0065. Min Act: -0.1700
Data Index: 8039132 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.0065. Min Act: -0.1700
Data Index: 4338220 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.9440. Min Act: -0.1700
Data Index: 955799 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.9440. Min Act: -0.1700
Data Index: 1384774 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5065. Min Range: -10.5065
Max Act: 10.0690. Min Act: -0.1700
Data Index: 5994410 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.9440. Min Act: -0.1700
Data Index: 673147 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.9440. Min Act: -0.1700
Data Index: 6850356 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.8815. Min Act: -0.1700
Data Index: 6208010 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.9440. Min Act: -0.1700
Data Index: 1094455 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.8815. Min Act: -0.1700
Data Index: 5487315 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.8815. Min Act: -0.1700
Data Index: 5136155 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.7565. Min Act: -0.1700
Data Index: 8373643 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5065. Min Range: -10.5065
Max Act: 9.8190. Min Act: -0.1700
Data Index: 5791308 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19