Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0976. Min Act: -0.1700
Data Index: 8140357 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0976. Min Act: -0.1700
Data Index: 6732148 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0808. Min Act: -0.1700
Data Index: 6602872 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0304. Min Act: -0.1700
Data Index: 6010276 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0640. Min Act: -0.1700
Data Index: 3258150 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0472. Min Act: -0.1700
Data Index: 7188321 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0640. Min Act: -0.1700
Data Index: 8750908 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0304. Min Act: -0.1700
Data Index: 5431003 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0304. Min Act: -0.1700
Data Index: 6212322 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0135. Min Act: -0.1699
Data Index: 4037867 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0976. Min Range: -2.0976
Max Act: 2.0135. Min Act: -0.1700
Data Index: 7069277 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9966. Min Act: -0.1699
Data Index: 2924883 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9966. Min Act: -0.1652
Data Index: 2328439 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9966. Min Act: -0.1700
Data Index: 76223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9966. Min Act: -0.1700
Data Index: 3105141 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9628. Min Act: -0.1700
Data Index: 1162226 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9797. Min Act: -0.1700
Data Index: 4747888 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9797. Min Act: -0.1700
Data Index: 7130349 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9797. Min Act: -0.1699
Data Index: 5343024 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0976. Min Range: -2.0976
Max Act: 1.9628. Min Act: -0.1699
Data Index: 168600 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19