Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5138 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.3720. Min Act: -0.1700
Data Index: 5416696 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.3095. Min Act: -0.1700
Data Index: 698313 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2783. Min Act: -0.1700
Data Index: 4450271 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2783. Min Act: -0.1700
Data Index: 3927558 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 2782557 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2470. Min Act: -0.1700
Data Index: 7068773 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2470. Min Act: -0.1700
Data Index: 1650185 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2470. Min Act: -0.1700
Data Index: 7358607 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 2283635 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 3854683 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.2158. Min Act: -0.1700
Data Index: 8642874 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1533. Min Act: -0.1700
Data Index: 5236509 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1845. Min Act: -0.1700
Data Index: 8671669 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1845. Min Act: -0.1700
Data Index: 1472493 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1845. Min Act: -0.1700
Data Index: 1182435 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1845. Min Act: -0.1700
Data Index: 2023098 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1533. Min Act: -0.1700
Data Index: 6838620 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1533. Min Act: -0.1700
Data Index: 1172834 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1533. Min Act: -0.1700
Data Index: 837058 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3720. Min Range: -5.3720
Max Act: 5.1533. Min Act: -0.1700
Data Index: 7068774 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19