Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1498 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0029. Min Range: -6.0029
Max Act: 6.0029. Min Act: -0.1700
Data Index: 5902153 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.9092. Min Act: -0.1700
Data Index: 8180717 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.7842. Min Act: -0.1700
Data Index: 46610 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.7217. Min Act: -0.1700
Data Index: 3552760 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 602786 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 8133770 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5415537 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 276667 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 557991 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 6761855 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6279. Min Act: -0.1700
Data Index: 8249997 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6904. Min Act: -0.1700
Data Index: 4708622 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6592. Min Act: -0.1700
Data Index: 4911439 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6279. Min Act: -0.1700
Data Index: 620077 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.6279. Min Act: -0.1700
Data Index: 5874544 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.5967. Min Act: -0.1700
Data Index: 5830722 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.5967. Min Act: -0.1700
Data Index: 8026779 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.5967. Min Act: -0.1700
Data Index: 156498 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.5342. Min Act: -0.1700
Data Index: 2570908 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0029. Min Range: -6.0029
Max Act: 5.5654. Min Act: -0.1700
Data Index: 6929638 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19