Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4775 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.6875. Min Act: -0.1700
Data Index: 7982043 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.6562. Min Act: -0.1700
Data Index: 4341045 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5937. Min Act: -0.1700
Data Index: 6878530 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5625. Min Act: -0.1700
Data Index: 7066704 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5625. Min Act: -0.1700
Data Index: 2949162 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5625. Min Act: -0.1700
Data Index: 7066703 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5625. Min Act: -0.1700
Data Index: 8740475 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5312. Min Act: -0.1700
Data Index: 2836522 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3421456 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5312. Min Act: -0.1700
Data Index: 7722450 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3279294 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5000. Min Act: -0.1700
Data Index: 5801272 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7522393 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4687. Min Act: -0.1700
Data Index: 835462 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4687. Min Act: -0.1700
Data Index: 133740 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4375. Min Act: -0.1700
Data Index: 3373524 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4687. Min Act: -0.1700
Data Index: 766064 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4375. Min Act: -0.1700
Data Index: 982614 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4375. Min Act: -0.1700
Data Index: 7128822 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6875. Min Range: -5.6875
Max Act: 5.4687. Min Act: -0.1700
Data Index: 1533164 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19