Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.7050. Min Act: -0.1145
Data Index: 5695654 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.6006. Min Act: -0.1607
Data Index: 4801025 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5918. Min Act: -0.1678
Data Index: 6791666 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5918. Min Act: -0.1678
Data Index: 969827 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5831. Min Act: -0.1573
Data Index: 1317026 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5918. Min Act: -0.1642
Data Index: 4007156 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5743. Min Act: -0.1469
Data Index: 965632 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5568. Min Act: -0.1700
Data Index: 5682317 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5481. Min Act: -0.1607
Data Index: 1463656 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5393. Min Act: -0.1361
Data Index: 6791665 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5306. Min Act: -0.1582
Data Index: 7862595 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5306. Min Act: -0.1435
Data Index: 2049912 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5043. Min Act: -0.1337
Data Index: 3628724 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5130. Min Act: -0.1603
Data Index: 7865671 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5043. Min Act: -0.1635
Data Index: 2804742 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5043. Min Act: -0.1674
Data Index: 2109427 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5043. Min Act: -0.1661
Data Index: 7054816 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.4955. Min Act: -0.1564
Data Index: 104765 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.5043. Min Act: -0.1582
Data Index: 1871625 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7050. Min Range: -1.7050
Max Act: 1.4955. Min Act: -0.1384
Data Index: 7695668 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19