Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0984. Min Act: -0.1700
Data Index: 36535 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0672. Min Act: -0.1700
Data Index: 3613653 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0359. Min Act: -0.1700
Data Index: 7296641 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0359. Min Act: -0.1700
Data Index: 5635510 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0359. Min Act: -0.1700
Data Index: 4350322 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0359. Min Act: -0.1700
Data Index: 4321728 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0359. Min Act: -0.1700
Data Index: 930571 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 4760521 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 1544172 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 1420085 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 358097 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 3379854 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 1351404 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0984. Min Range: -5.0984
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3181677 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2917275 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2672556 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2537858 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2053162 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 2033041 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0984. Min Range: -5.0984
Max Act: 5.0047. Min Act: -0.1700
Data Index: 1926400 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19