Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0187. Min Range: -5.0187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6063695 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0187. Min Range: -5.0187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 2175875 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.9562. Min Act: -0.1700
Data Index: 5837328 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8312. Min Act: -0.1700
Data Index: 3066531 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8312. Min Act: -0.1700
Data Index: 5479494 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8000. Min Act: -0.1700
Data Index: 1455351 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8000. Min Act: -0.1700
Data Index: 7573513 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8000. Min Act: -0.1700
Data Index: 8251478 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8000. Min Act: -0.1700
Data Index: 7292705 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 6605406 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 7762169 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 2902924 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 5128017 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 2459132 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 8805832 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 5919005 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 4253936 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 4786695 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7062. Min Act: -0.1700
Data Index: 6063696 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7062. Min Act: -0.1700
Data Index: 1117585 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19