Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2539. Min Range: -6.2539
Max Act: 6.2227. Min Act: -0.1700
Data Index: 5020780 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2539. Min Range: -6.2539
Max Act: 6.2539. Min Act: -0.1700
Data Index: 4755653 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.9414. Min Act: -0.1700
Data Index: 3533736 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.9414. Min Act: -0.1700
Data Index: 4549217 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.9414. Min Act: -0.1700
Data Index: 2849444 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.9102. Min Act: -0.1700
Data Index: 5165797 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.8789. Min Act: -0.1700
Data Index: 1409261 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.8789. Min Act: -0.1700
Data Index: 1426069 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.8789. Min Act: -0.1700
Data Index: 4170902 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.8164. Min Act: -0.1700
Data Index: 4697507 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7852. Min Act: -0.1700
Data Index: 7261662 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7852. Min Act: -0.1700
Data Index: 4172487 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7852. Min Act: -0.1700
Data Index: 423815 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7539. Min Act: -0.1700
Data Index: 4077993 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7227. Min Act: -0.1700
Data Index: 3433700 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7539. Min Act: -0.1700
Data Index: 4833065 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7227. Min Act: -0.1700
Data Index: 7155028 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.7227. Min Act: -0.1700
Data Index: 4813535 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.6914. Min Act: -0.1700
Data Index: 3039790 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2539. Min Range: -6.2539
Max Act: 5.6914. Min Act: -0.1700
Data Index: 334588 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19