Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4356 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.9438. Min Act: -0.1700
Data Index: 7354373 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.9126. Min Act: -0.1700
Data Index: 4300631 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.8813. Min Act: -0.1700
Data Index: 704798 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.8813. Min Act: -0.1700
Data Index: 4955082 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.8813. Min Act: -0.1700
Data Index: 7995948 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.8501. Min Act: -0.1700
Data Index: 7372212 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.8188. Min Act: -0.1700
Data Index: 6520016 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7876. Min Act: -0.1700
Data Index: 1363622 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7876. Min Act: -0.1700
Data Index: 7378952 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7876. Min Act: -0.1700
Data Index: 4298024 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7563. Min Act: -0.1700
Data Index: 8700965 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7563. Min Act: -0.1700
Data Index: 2025526 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7563. Min Act: -0.1700
Data Index: 8269891 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7563. Min Act: -0.1700
Data Index: 4451571 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7563. Min Act: -0.1700
Data Index: 7895592 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7251. Min Act: -0.1700
Data Index: 3409523 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7251. Min Act: -0.1700
Data Index: 496628 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7563. Min Act: -0.1700
Data Index: 2982117 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7251. Min Act: -0.1700
Data Index: 6787272 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9438. Min Range: -4.9438
Max Act: 4.7251. Min Act: -0.1700
Data Index: 446745 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19