Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 581 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1837. Min Act: -0.1700
Data Index: 8015226 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1212. Min Act: -0.1700
Data Index: 7299903 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3906131 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0899. Min Act: -0.1700
Data Index: 4649110 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0587. Min Act: -0.1700
Data Index: 6513261 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1837. Min Range: -5.1837
Max Act: 5.0587. Min Act: -0.1700
Data Index: 5576379 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9962. Min Act: -0.1700
Data Index: 6599579 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9649. Min Act: -0.1700
Data Index: 4911025 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9649. Min Act: -0.1700
Data Index: 4911026 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9024. Min Act: -0.1700
Data Index: 6599581 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.9024. Min Act: -0.1700
Data Index: 3072190 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8712. Min Act: -0.1700
Data Index: 5652529 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8712. Min Act: -0.1700
Data Index: 6397693 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8712. Min Act: -0.1700
Data Index: 8714694 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8712. Min Act: -0.1700
Data Index: 6015190 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8399. Min Act: -0.1700
Data Index: 94568 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8712. Min Act: -0.1700
Data Index: 4627992 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8087. Min Act: -0.1700
Data Index: 1780101 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8399. Min Act: -0.1700
Data Index: 3412347 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1837. Min Range: -5.1837
Max Act: 4.8399. Min Act: -0.1700
Data Index: 1861382 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19