Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4625 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.5649. Min Act: -0.1700
Data Index: 8759834 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.2837. Min Act: -0.1700
Data Index: 7656169 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.2524. Min Act: -0.1700
Data Index: 850669 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.1899. Min Act: -0.1700
Data Index: 1352661 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.2212. Min Act: -0.1700
Data Index: 6941784 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.1587. Min Act: -0.1700
Data Index: 1710935 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.1274. Min Act: -0.1700
Data Index: 1816275 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6209650 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6579003 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0962. Min Act: -0.1700
Data Index: 5288845 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0962. Min Act: -0.1700
Data Index: 4083300 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0649. Min Act: -0.1700
Data Index: 4083298 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0649. Min Act: -0.1700
Data Index: 5990298 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0962. Min Act: -0.1700
Data Index: 1303621 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2034400 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0649. Min Act: -0.1700
Data Index: 4039210 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7089995 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0649. Min Act: -0.1700
Data Index: 5596652 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0337. Min Act: -0.1700
Data Index: 121191 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5649. Min Range: -5.5649
Max Act: 5.0337. Min Act: -0.1700
Data Index: 8537310 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19