Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1245 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.9437. Min Act: -0.1700
Data Index: 5083354 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.8500. Min Act: -0.1700
Data Index: 4098632 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.7875. Min Act: -0.1700
Data Index: 8794430 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.7875. Min Act: -0.1700
Data Index: 4266782 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.7562. Min Act: -0.1700
Data Index: 8613695 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.7250. Min Act: -0.1700
Data Index: 5677480 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.6312. Min Act: -0.1700
Data Index: 1737858 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.6312. Min Act: -0.1700
Data Index: 1964682 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.6625. Min Act: -0.1700
Data Index: 5439972 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5687. Min Act: -0.1700
Data Index: 6039567 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5687. Min Act: -0.1700
Data Index: 1025586 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5687. Min Act: -0.1700
Data Index: 8293315 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5375. Min Act: -0.1700
Data Index: 4686227 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5375. Min Act: -0.1700
Data Index: 1797887 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5375. Min Act: -0.1700
Data Index: 2984517 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5062. Min Act: -0.1700
Data Index: 5196710 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5062. Min Act: -0.1700
Data Index: 4666242 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5062. Min Act: -0.1700
Data Index: 1287104 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5062. Min Act: -0.1700
Data Index: 3432816 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9437. Min Range: -6.9437
Max Act: 6.5062. Min Act: -0.1700
Data Index: 5866214 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19