Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1782. Min Range: -6.1782
Max Act: 6.1782. Min Act: -0.1700
Data Index: 4952808 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1782. Min Range: -6.1782
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3785549 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1782. Min Range: -6.1782
Max Act: 6.0220. Min Act: -0.1700
Data Index: 7549687 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.9595. Min Act: -0.1700
Data Index: 929106 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.9282. Min Act: -0.1700
Data Index: 675774 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.8970. Min Act: -0.1700
Data Index: 1964322 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.8657. Min Act: -0.1700
Data Index: 8665389 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.8032. Min Act: -0.1700
Data Index: 3318355 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.8032. Min Act: -0.1700
Data Index: 7377336 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7720. Min Act: -0.1700
Data Index: 1103709 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7720. Min Act: -0.1700
Data Index: 1408449 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7407. Min Act: -0.1700
Data Index: 961511 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7095. Min Act: -0.1700
Data Index: 1954072 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7720. Min Act: -0.1700
Data Index: 1714289 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7407. Min Act: -0.1700
Data Index: 1865915 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.6782. Min Act: -0.1700
Data Index: 3165371 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7095. Min Act: -0.1700
Data Index: 1472030 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7095. Min Act: -0.1700
Data Index: 2915536 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7095. Min Act: -0.1700
Data Index: 5079603 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1782. Min Range: -6.1782
Max Act: 5.7095. Min Act: -0.1700
Data Index: 570066 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19