Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4990 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.2587. Min Act: -0.1700
Data Index: 2895419 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.1024. Min Act: -0.1700
Data Index: 7624855 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.0712. Min Act: -0.1700
Data Index: 7330331 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.0086. Min Act: -0.1700
Data Index: 789762 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.0399. Min Act: -0.1700
Data Index: 7485105 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9774. Min Act: -0.1700
Data Index: 4773723 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9774. Min Act: -0.1700
Data Index: 5142749 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.0086. Min Act: -0.1700
Data Index: 2765237 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9774. Min Act: -0.1700
Data Index: 8831809 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2587. Min Range: -4.2587
Max Act: 4.0086. Min Act: -0.1700
Data Index: 7665410 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9149. Min Act: -0.1700
Data Index: 3195177 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9461. Min Act: -0.1700
Data Index: 7070164 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9461. Min Act: -0.1700
Data Index: 5469935 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9461. Min Act: -0.1700
Data Index: 2645160 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9774. Min Act: -0.1700
Data Index: 559674 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9461. Min Act: -0.1700
Data Index: 6068499 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9149. Min Act: -0.1700
Data Index: 3770119 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9149. Min Act: -0.1700
Data Index: 2762800 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.9149. Min Act: -0.1700
Data Index: 6675769 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2587. Min Range: -4.2587
Max Act: 3.8836. Min Act: -0.1700
Data Index: 2634786 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19