Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.5262. Min Act: -0.1700
Data Index: 2117241 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.4637. Min Act: -0.1700
Data Index: 1989716 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.3699. Min Act: -0.1700
Data Index: 2872721 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.2762. Min Act: -0.1700
Data Index: 1688294 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.1824. Min Act: -0.1700
Data Index: 8585803 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.1824. Min Act: -0.1700
Data Index: 6558276 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.1512. Min Act: -0.1700
Data Index: 2956966 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.1199. Min Act: -0.1700
Data Index: 889087 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0887. Min Act: -0.1700
Data Index: 1751107 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0887. Min Act: -0.1700
Data Index: 5183248 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0574. Min Act: -0.1700
Data Index: 7907626 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0574. Min Act: -0.1700
Data Index: 6590446 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0262. Min Act: -0.1700
Data Index: 7441727 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0574. Min Act: -0.1700
Data Index: 5081118 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0262. Min Act: -0.1700
Data Index: 3758938 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5262. Min Range: -6.5262
Max Act: 6.0262. Min Act: -0.1700
Data Index: 6614745 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5262. Min Range: -6.5262
Max Act: 5.9949. Min Act: -0.1700
Data Index: 3873929 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5262. Min Range: -6.5262
Max Act: 5.9949. Min Act: -0.1700
Data Index: 1913768 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5262. Min Range: -6.5262
Max Act: 5.9637. Min Act: -0.1700
Data Index: 4986851 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5262. Min Range: -6.5262
Max Act: 5.9637. Min Act: -0.1700
Data Index: 36268 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19