Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.8801. Min Act: -0.1700
Data Index: 1864633 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.8176. Min Act: -0.1700
Data Index: 136766 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.7551. Min Act: -0.1700
Data Index: 2565398 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.7551. Min Act: -0.1700
Data Index: 136764 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.6926. Min Act: -0.1700
Data Index: 5767114 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.6926. Min Act: -0.1700
Data Index: 2929026 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.6926. Min Act: -0.1700
Data Index: 4695817 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.6926. Min Act: -0.1700
Data Index: 1811773 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.6301. Min Act: -0.1700
Data Index: 1811771 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.5676. Min Act: -0.1700
Data Index: 5111059 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.5051. Min Act: -0.1700
Data Index: 136765 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.4426. Min Act: -0.1700
Data Index: 136763 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.4426. Min Act: -0.1700
Data Index: 1811774 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.4426. Min Act: -0.1700
Data Index: 6839019 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.3801. Min Act: -0.1700
Data Index: 1811775 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.3176. Min Act: -0.1700
Data Index: 6601394 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.3176. Min Act: -0.1700
Data Index: 4695816 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.2551. Min Act: -0.1700
Data Index: 6339205 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.2551. Min Act: -0.1700
Data Index: 1540128 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8801. Min Range: -8.8801
Max Act: 8.1926. Min Act: -0.1700
Data Index: 306500 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19