Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.7188. Min Act: -0.1700
Data Index: 3658121 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.5625. Min Act: -0.1700
Data Index: 4538315 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.2500. Min Act: -0.1700
Data Index: 2667801 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.2813. Min Act: -0.1700
Data Index: 5474671 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.1563. Min Act: -0.1700
Data Index: 4047491 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.0938. Min Act: -0.1700
Data Index: 4013603 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4243814 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6782253 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.0000. Min Act: -0.1700
Data Index: 7651960 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9688. Min Act: -0.1700
Data Index: 709322 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9375. Min Act: -0.1700
Data Index: 5743647 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7188. Min Range: -6.7188
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6594275 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9688. Min Act: -0.1700
Data Index: 1106002 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9688. Min Act: -0.1700
Data Index: 967675 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9688. Min Act: -0.1700
Data Index: 49821 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9375. Min Act: -0.1700
Data Index: 6792895 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9375. Min Act: -0.1700
Data Index: 6356221 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9063. Min Act: -0.1700
Data Index: 7375077 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9063. Min Act: -0.1700
Data Index: 4522915 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7188. Min Range: -6.7188
Max Act: 5.9063. Min Act: -0.1700
Data Index: 1508845 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19