Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 890 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1001. Min Range: -7.1001
Max Act: 7.1001. Min Act: -0.1700
Data Index: 8646700 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9751. Min Act: -0.1700
Data Index: 5006900 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9751. Min Act: -0.1700
Data Index: 1811068 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9751. Min Act: -0.1700
Data Index: 1495077 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9751. Min Act: -0.1700
Data Index: 5919552 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9438. Min Act: -0.1700
Data Index: 7627814 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9126. Min Act: -0.1700
Data Index: 5635527 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.9126. Min Act: -0.1700
Data Index: 6951957 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.8813. Min Act: -0.1700
Data Index: 558858 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.8813. Min Act: -0.1700
Data Index: 160131 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.8501. Min Act: -0.1700
Data Index: 2185772 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.8188. Min Act: -0.1700
Data Index: 1915357 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.8188. Min Act: -0.1700
Data Index: 645400 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 8770438 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 4210502 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 6271973 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 4130204 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7251. Min Act: -0.1700
Data Index: 512501 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7563. Min Act: -0.1700
Data Index: 1876751 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1001. Min Range: -7.1001
Max Act: 6.7563. Min Act: -0.1700
Data Index: 1396482 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19