Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.4793. Min Act: -0.1700
Data Index: 4201014 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.3543. Min Act: -0.1700
Data Index: 7420062 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1980. Min Act: -0.1700
Data Index: 7032514 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2605. Min Act: -0.1700
Data Index: 5886814 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2293. Min Act: -0.1700
Data Index: 4755463 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1980. Min Act: -0.1700
Data Index: 4562722 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.2293. Min Act: -0.1700
Data Index: 3705914 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1980. Min Act: -0.1700
Data Index: 2798766 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 7185644 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 4447025 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1355. Min Act: -0.1700
Data Index: 3595977 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 6983108 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 1180211 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 838424 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1980. Min Act: -0.1700
Data Index: 7977483 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 7957526 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1668. Min Act: -0.1700
Data Index: 6141907 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1355. Min Act: -0.1700
Data Index: 256131 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1355. Min Act: -0.1700
Data Index: 6918886 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4793. Min Range: -6.4793
Max Act: 6.1355. Min Act: -0.1700
Data Index: 6499080 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19