Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 816 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.9900. Min Act: -0.1700
Data Index: 4440378 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.9275. Min Act: -0.1700
Data Index: 7846433 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.8963. Min Act: -0.1700
Data Index: 8406575 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.8963. Min Act: -0.1700
Data Index: 6995507 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.8338. Min Act: -0.1700
Data Index: 7794041 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.8025. Min Act: -0.1700
Data Index: 6461299 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.8025. Min Act: -0.1700
Data Index: 1616738 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.8025. Min Act: -0.1700
Data Index: 7408301 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7713. Min Act: -0.1700
Data Index: 4903725 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7713. Min Act: -0.1700
Data Index: 83841 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7713. Min Act: -0.1700
Data Index: 879793 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7713. Min Act: -0.1700
Data Index: 1009611 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7713. Min Act: -0.1700
Data Index: 145514 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7400. Min Act: -0.1700
Data Index: 7899562 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7088. Min Act: -0.1700
Data Index: 6995503 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7088. Min Act: -0.1700
Data Index: 6867279 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7088. Min Act: -0.1700
Data Index: 4874572 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.7088. Min Act: -0.1700
Data Index: 4847678 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.6775. Min Act: -0.1700
Data Index: 7846427 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9900. Min Range: -6.9900
Max Act: 6.6775. Min Act: -0.1700
Data Index: 3436736 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19