Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5636 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0058. Min Range: -3.0058
Max Act: 3.0058. Min Act: -0.1700
Data Index: 7967372 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2784033 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 1545281 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2863291 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 859459 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2516839 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2560240 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 37661 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 704255 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 573442 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2446288 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 850212 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2232718 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 1147458 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 769639 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 1126008 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 2885235 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 1734889 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 56782 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9267. Min Act: -0.1700
Data Index: 416117 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19