Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.6250. Min Act: -0.1700
Data Index: 7008963 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.5000. Min Act: -0.1700
Data Index: 4932325 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.1250. Min Act: -0.1700
Data Index: 4743243 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.0937. Min Act: -0.1700
Data Index: 8651952 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.0625. Min Act: -0.1700
Data Index: 6379718 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.0000. Min Act: -0.1700
Data Index: 5063785 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6250. Min Range: -6.6250
Max Act: 6.0000. Min Act: -0.1700
Data Index: 5128694 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.9062. Min Act: -0.1700
Data Index: 2136894 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.8125. Min Act: -0.1700
Data Index: 3260955 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.7812. Min Act: -0.1700
Data Index: 4166239 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.7187. Min Act: -0.1700
Data Index: 6160218 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.7500. Min Act: -0.1700
Data Index: 6370719 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.7187. Min Act: -0.1700
Data Index: 1684780 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.7187. Min Act: -0.1700
Data Index: 5764317 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.7500. Min Act: -0.1700
Data Index: 4840176 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.6875. Min Act: -0.1700
Data Index: 7862437 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.6875. Min Act: -0.1700
Data Index: 7157524 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.6875. Min Act: -0.1700
Data Index: 6389219 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.6562. Min Act: -0.1700
Data Index: 5882552 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6250. Min Range: -6.6250
Max Act: 5.6562. Min Act: -0.1700
Data Index: 6034207 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19