Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5327 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.4769. Min Act: -0.1700
Data Index: 2381456 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.4144. Min Act: -0.1700
Data Index: 6365761 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.3519. Min Act: -0.1700
Data Index: 4336182 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.3519. Min Act: -0.1700
Data Index: 3686684 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.2894. Min Act: -0.1700
Data Index: 5779357 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.2269. Min Act: -0.1700
Data Index: 7923527 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1644. Min Act: -0.1700
Data Index: 5789494 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1644. Min Act: -0.1700
Data Index: 8529174 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1644. Min Act: -0.1700
Data Index: 4871082 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1644. Min Act: -0.1700
Data Index: 5706034 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6188199 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1019. Min Act: -0.1700
Data Index: 4464103 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6471746 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.0394. Min Act: -0.1700
Data Index: 2307771 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.0394. Min Act: -0.1700
Data Index: 2799583 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4769. Min Range: -8.4769
Max Act: 8.1019. Min Act: -0.1700
Data Index: 6299528 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4769. Min Range: -8.4769
Max Act: 7.9769. Min Act: -0.1700
Data Index: 1609076 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4769. Min Range: -8.4769
Max Act: 7.9769. Min Act: -0.1700
Data Index: 5273649 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4769. Min Range: -8.4769
Max Act: 7.9769. Min Act: -0.1700
Data Index: 5143886 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4769. Min Range: -8.4769
Max Act: 7.9144. Min Act: -0.1700
Data Index: 821492 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19