Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.1821. Min Act: -0.1700
Data Index: 12046 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.1509. Min Act: -0.1700
Data Index: 1934518 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.0884. Min Act: -0.1700
Data Index: 8236511 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.0571. Min Act: -0.1700
Data Index: 3012339 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.0571. Min Act: -0.1700
Data Index: 1236951 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3758146 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1821. Min Range: -5.1821
Max Act: 5.0259. Min Act: -0.1700
Data Index: 6952876 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9634. Min Act: -0.1700
Data Index: 8161875 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9634. Min Act: -0.1700
Data Index: 5285749 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9634. Min Act: -0.1700
Data Index: 5277687 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9634. Min Act: -0.1700
Data Index: 689675 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9321. Min Act: -0.1700
Data Index: 4055860 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9009. Min Act: -0.1700
Data Index: 1501423 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9009. Min Act: -0.1700
Data Index: 862536 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.9009. Min Act: -0.1700
Data Index: 7825143 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.8696. Min Act: -0.1700
Data Index: 4801787 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.8696. Min Act: -0.1700
Data Index: 8278890 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.8696. Min Act: -0.1700
Data Index: 4682246 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.8384. Min Act: -0.1700
Data Index: 7266166 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1821. Min Range: -5.1821
Max Act: 4.8384. Min Act: -0.1700
Data Index: 1686565 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19