Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0631. Min Range: -3.0631
Max Act: 3.0631. Min Act: -0.1700
Data Index: 1451791 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.7778. Min Act: -0.1700
Data Index: 1411834 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.7778. Min Act: -0.1700
Data Index: 2689787 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.7299. Min Act: -0.1700
Data Index: 6685031 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.7139. Min Act: -0.1700
Data Index: 1319256 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.7299. Min Act: -0.1700
Data Index: 5687940 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6979. Min Act: -0.1700
Data Index: 1702982 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6979. Min Act: -0.1700
Data Index: 7757019 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6819. Min Act: -0.1700
Data Index: 8724664 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6819. Min Act: -0.1700
Data Index: 8346056 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6498. Min Act: -0.1700
Data Index: 3203544 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6819. Min Act: -0.1700
Data Index: 3574892 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6819. Min Act: -0.1700
Data Index: 1594925 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6659. Min Act: -0.1700
Data Index: 4473896 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6498. Min Act: -0.1700
Data Index: 4716016 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6498. Min Act: -0.1700
Data Index: 8724665 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6498. Min Act: -0.1700
Data Index: 1928861 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6498. Min Act: -0.1700
Data Index: 5309392 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6498. Min Act: -0.1700
Data Index: 8223659 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0631. Min Range: -3.0631
Max Act: 2.6338. Min Act: -0.1700
Data Index: 5015848 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19