Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3502. Min Range: -10.3502
Max Act: 10.3502. Min Act: -0.1700
Data Index: 5894859 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3502. Min Range: -10.3502
Max Act: 10.1002. Min Act: -0.1700
Data Index: 5293608 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.9752. Min Act: -0.1700
Data Index: 1033669 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.9752. Min Act: -0.1700
Data Index: 4604738 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.9127. Min Act: -0.1700
Data Index: 1033667 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.9127. Min Act: -0.1700
Data Index: 8591551 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.8502. Min Act: -0.1700
Data Index: 4263780 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7877. Min Act: -0.1700
Data Index: 1714380 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7877. Min Act: -0.1700
Data Index: 1250565 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 1121843 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 6862736 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 1807544 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 2079127 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 7755716 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 8071561 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 8298216 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 6631850 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 6112801 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.7252. Min Act: -0.1700
Data Index: 6385655 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3502. Min Range: -10.3502
Max Act: 9.6627. Min Act: -0.1700
Data Index: 3778512 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19