Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4762 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.7734. Min Act: -0.1700
Data Index: 1845925 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.4922. Min Act: -0.1700
Data Index: 8241839 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.1797. Min Act: -0.1700
Data Index: 8241815 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.9922. Min Act: -0.1700
Data Index: 5392963 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.8359. Min Act: -0.1700
Data Index: 575917 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.7734. Min Act: -0.1700
Data Index: 6747204 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.8047. Min Act: -0.1700
Data Index: 6219977 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.7734. Min Act: -0.1700
Data Index: 2096821 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.7422. Min Act: -0.1700
Data Index: 740291 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.7109. Min Act: -0.1700
Data Index: 68787 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.7109. Min Act: -0.1700
Data Index: 8674372 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.6172. Min Act: -0.1700
Data Index: 6413666 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.6484. Min Act: -0.1700
Data Index: 7705410 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 2688428 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 3313447 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 649863 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5859. Min Act: -0.1700
Data Index: 91893 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 5953679 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5234. Min Act: -0.1700
Data Index: 8645754 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7734. Min Range: -6.7734
Max Act: 5.5547. Min Act: -0.1700
Data Index: 4937986 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19