Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4224 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0840. Min Range: -8.0840
Max Act: 8.0840. Min Act: -0.1700
Data Index: 2523447 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0840. Min Range: -8.0840
Max Act: 8.0215. Min Act: -0.1700
Data Index: 8617745 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.9590. Min Act: -0.1700
Data Index: 7994527 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.9590. Min Act: -0.1700
Data Index: 875400 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8965. Min Act: -0.1700
Data Index: 6103427 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 6647511 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 5084211 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 5665841 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 2311633 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 4626022 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 3969298 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 2769828 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 8633965 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.8340. Min Act: -0.1700
Data Index: 2568155 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.7715. Min Act: -0.1700
Data Index: 3127415 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.7715. Min Act: -0.1700
Data Index: 6699951 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.7715. Min Act: -0.1700
Data Index: 6866561 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.7715. Min Act: -0.1700
Data Index: 2154665 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.7715. Min Act: -0.1700
Data Index: 7114748 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0840. Min Range: -8.0840
Max Act: 7.7715. Min Act: -0.1700
Data Index: 2341779 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19