Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.4582. Min Act: -0.1700
Data Index: 2267020 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.4582. Min Act: -0.1700
Data Index: 959999 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.3645. Min Act: -0.1700
Data Index: 1176813 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.3645. Min Act: -0.1700
Data Index: 7896704 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.2707. Min Act: -0.1700
Data Index: 2957150 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.2082. Min Act: -0.1700
Data Index: 305223 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.1770. Min Act: -0.1700
Data Index: 5249764 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.1457. Min Act: -0.1700
Data Index: 1606464 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.1457. Min Act: -0.1700
Data Index: 5494855 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.1145. Min Act: -0.1700
Data Index: 7336016 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.1145. Min Act: -0.1700
Data Index: 881435 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0832. Min Act: -0.1700
Data Index: 5800851 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0832. Min Act: -0.1700
Data Index: 4198049 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0832. Min Act: -0.1700
Data Index: 2162662 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0832. Min Act: -0.1700
Data Index: 6658298 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0520. Min Act: -0.1700
Data Index: 8498586 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0520. Min Act: -0.1700
Data Index: 8818405 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4582. Min Range: -5.4582
Max Act: 4.9895. Min Act: -0.1700
Data Index: 2747741 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4582. Min Range: -5.4582
Max Act: 5.0207. Min Act: -0.1700
Data Index: 8773020 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4582. Min Range: -5.4582
Max Act: 4.9895. Min Act: -0.1700
Data Index: 2579766 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19