Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2876. Min Range: -6.2876
Max Act: 6.2876. Min Act: -0.1700
Data Index: 3530340 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2876. Min Range: -6.2876
Max Act: 6.1001. Min Act: -0.1700
Data Index: 5009867 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2876. Min Range: -6.2876
Max Act: 6.1001. Min Act: -0.1700
Data Index: 4552801 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.9751. Min Act: -0.1700
Data Index: 7359603 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2876. Min Range: -6.2876
Max Act: 6.0376. Min Act: -0.1700
Data Index: 7467468 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.8501. Min Act: -0.1700
Data Index: 6642123 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.8501. Min Act: -0.1700
Data Index: 5238034 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.8188. Min Act: -0.1700
Data Index: 5687370 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7876. Min Act: -0.1700
Data Index: 4759255 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.8188. Min Act: -0.1700
Data Index: 2555632 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7563. Min Act: -0.1700
Data Index: 8360367 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7876. Min Act: -0.1700
Data Index: 686881 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.8188. Min Act: -0.1700
Data Index: 5181188 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7876. Min Act: -0.1700
Data Index: 6200549 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.8188. Min Act: -0.1700
Data Index: 473780 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7563. Min Act: -0.1700
Data Index: 3614790 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.6938. Min Act: -0.1700
Data Index: 1790757 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7251. Min Act: -0.1700
Data Index: 8064208 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7251. Min Act: -0.1700
Data Index: 841892 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2876. Min Range: -6.2876
Max Act: 5.7563. Min Act: -0.1700
Data Index: 4277957 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19