Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.5542. Min Act: -0.1700
Data Index: 6014025 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.4917. Min Act: -0.1700
Data Index: 6936761 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.3667. Min Act: -0.1700
Data Index: 6022510 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.3042. Min Act: -0.1700
Data Index: 7486232 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.3042. Min Act: -0.1700
Data Index: 1108796 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.3667. Min Act: -0.1700
Data Index: 96396 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.2417. Min Act: -0.1700
Data Index: 5258891 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.1167. Min Act: -0.1700
Data Index: 5634031 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.0542. Min Act: -0.1700
Data Index: 2930650 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.1167. Min Act: -0.1700
Data Index: 6359892 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.0229. Min Act: -0.1700
Data Index: 5312093 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.0542. Min Act: -0.1700
Data Index: 4457633 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.0229. Min Act: -0.1700
Data Index: 5563526 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.0229. Min Act: -0.1700
Data Index: 6538371 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5542. Min Range: -8.5542
Max Act: 8.0229. Min Act: -0.1700
Data Index: 15986 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5542. Min Range: -8.5542
Max Act: 7.9604. Min Act: -0.1700
Data Index: 5771080 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5542. Min Range: -8.5542
Max Act: 7.9292. Min Act: -0.1700
Data Index: 1969915 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5542. Min Range: -8.5542
Max Act: 7.9292. Min Act: -0.1700
Data Index: 7125516 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5542. Min Range: -8.5542
Max Act: 7.9292. Min Act: -0.1700
Data Index: 4560138 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5542. Min Range: -8.5542
Max Act: 7.9292. Min Act: -0.1700
Data Index: 2580774 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19