Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.6014. Min Act: -0.1700
Data Index: 6930699 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.4139. Min Act: -0.1700
Data Index: 1557767 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.2576. Min Act: -0.1700
Data Index: 8420542 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.2264. Min Act: -0.1700
Data Index: 8782998 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.1326. Min Act: -0.1700
Data Index: 1931369 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.0389. Min Act: -0.1700
Data Index: 607341 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6014. Min Range: -6.6014
Max Act: 6.0076. Min Act: -0.1700
Data Index: 4327374 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9451. Min Act: -0.1700
Data Index: 6031025 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9764. Min Act: -0.1700
Data Index: 376418 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9764. Min Act: -0.1700
Data Index: 735493 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9764. Min Act: -0.1700
Data Index: 7549810 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9764. Min Act: -0.1700
Data Index: 5471274 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9451. Min Act: -0.1700
Data Index: 6807963 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9139. Min Act: -0.1700
Data Index: 7477089 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9139. Min Act: -0.1700
Data Index: 440371 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.9139. Min Act: -0.1700
Data Index: 416876 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.8826. Min Act: -0.1700
Data Index: 2961199 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.8826. Min Act: -0.1700
Data Index: 2554683 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.8826. Min Act: -0.1700
Data Index: 7244200 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6014. Min Range: -6.6014
Max Act: 5.8826. Min Act: -0.1700
Data Index: 2679107 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19