Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.8875. Min Act: -0.1700
Data Index: 5566912 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.8563. Min Act: -0.1700
Data Index: 5124255 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.8250. Min Act: -0.1700
Data Index: 588683 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7938. Min Act: -0.1700
Data Index: 801717 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7938. Min Act: -0.1700
Data Index: 8728116 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7938. Min Act: -0.1700
Data Index: 8165294 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7909969 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7938. Min Act: -0.1700
Data Index: 280525 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7625. Min Act: -0.1700
Data Index: 6375387 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7313. Min Act: -0.1700
Data Index: 416964 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7313. Min Act: -0.1700
Data Index: 170718 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7313. Min Act: -0.1700
Data Index: 7930468 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7000. Min Act: -0.1700
Data Index: 522955 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7000. Min Act: -0.1700
Data Index: 5767513 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.6688. Min Act: -0.1700
Data Index: 2899918 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7000. Min Act: -0.1700
Data Index: 7920398 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7000. Min Act: -0.1700
Data Index: 416603 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.7000. Min Act: -0.1700
Data Index: 4879531 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.6375. Min Act: -0.1700
Data Index: 2007055 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8875. Min Range: -5.8875
Max Act: 5.6688. Min Act: -0.1700
Data Index: 4830700 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19