Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0848. Min Range: -8.0848
Max Act: 8.0848. Min Act: -0.1700
Data Index: 5522455 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0848. Min Range: -8.0848
Max Act: 8.0223. Min Act: -0.1700
Data Index: 6965972 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0848. Min Range: -8.0848
Max Act: 8.0223. Min Act: -0.1700
Data Index: 2639426 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.9910. Min Act: -0.1700
Data Index: 2250627 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.9910. Min Act: -0.1700
Data Index: 4910670 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.8035. Min Act: -0.1700
Data Index: 8482944 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.8035. Min Act: -0.1700
Data Index: 5792053 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.8035. Min Act: -0.1700
Data Index: 3795035 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.7723. Min Act: -0.1700
Data Index: 6589090 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.7410. Min Act: -0.1700
Data Index: 7766232 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.7098. Min Act: -0.1700
Data Index: 6607108 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.7098. Min Act: -0.1700
Data Index: 2477771 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.6785. Min Act: -0.1700
Data Index: 4791447 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.6785. Min Act: -0.1700
Data Index: 3968838 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.6473. Min Act: -0.1700
Data Index: 713096 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.6473. Min Act: -0.1700
Data Index: 4928881 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.5848. Min Act: -0.1700
Data Index: 2745931 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.5848. Min Act: -0.1700
Data Index: 2396036 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.5848. Min Act: -0.1700
Data Index: 3956865 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0848. Min Range: -8.0848
Max Act: 7.5535. Min Act: -0.1700
Data Index: 5662507 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19