Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1224 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.7373. Min Act: -0.1700
Data Index: 6059019 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.4561. Min Act: -0.1700
Data Index: 4519810 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.4561. Min Act: -0.1700
Data Index: 4266067 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.4248. Min Act: -0.1700
Data Index: 4211380 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.3936. Min Act: -0.1700
Data Index: 6573692 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.3936. Min Act: -0.1700
Data Index: 5870706 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.3936. Min Act: -0.1700
Data Index: 400900 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.3936. Min Act: -0.1700
Data Index: 3009668 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.3623. Min Act: -0.1700
Data Index: 7207039 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.3936. Min Act: -0.1700
Data Index: 7207045 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2998. Min Act: -0.1700
Data Index: 7079526 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2998. Min Act: -0.1700
Data Index: 299504 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2998. Min Act: -0.1700
Data Index: 365685 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2998. Min Act: -0.1700
Data Index: 3975425 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2998. Min Act: -0.1700
Data Index: 486976 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2998. Min Act: -0.1700
Data Index: 6839658 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2686. Min Act: -0.1700
Data Index: 7841701 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2686. Min Act: -0.1700
Data Index: 688542 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2686. Min Act: -0.1700
Data Index: 7921876 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7373. Min Range: -5.7373
Max Act: 5.2373. Min Act: -0.1700
Data Index: 6059020 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19