Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1194. Min Range: -6.1194
Max Act: 6.1194. Min Act: -0.1700
Data Index: 3611144 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9006. Min Act: -0.1700
Data Index: 6016272 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8694. Min Act: -0.1700
Data Index: 8501249 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8381. Min Act: -0.1700
Data Index: 8423753 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.7131. Min Act: -0.1700
Data Index: 7765406 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6819. Min Act: -0.1700
Data Index: 2240781 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6819. Min Act: -0.1700
Data Index: 2374863 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6506. Min Act: -0.1700
Data Index: 1313153 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6506. Min Act: -0.1700
Data Index: 6496660 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6506. Min Act: -0.1700
Data Index: 2248060 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6506. Min Act: -0.1700
Data Index: 7890510 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.5881. Min Act: -0.1700
Data Index: 5843022 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6194. Min Act: -0.1700
Data Index: 7775345 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.5881. Min Act: -0.1700
Data Index: 7183016 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6194. Min Act: -0.1700
Data Index: 5982814 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.6194. Min Act: -0.1700
Data Index: 800123 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.5881. Min Act: -0.1700
Data Index: 7382400 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.5881. Min Act: -0.1700
Data Index: 3299134 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.5569. Min Act: -0.1700
Data Index: 7874720 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.5569. Min Act: -0.1700
Data Index: 6390633 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19