Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.6180. Min Act: -0.1700
Data Index: 5537404 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.6180. Min Act: -0.1700
Data Index: 3040184 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.6180. Min Act: -0.1700
Data Index: 4250175 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1931865 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 2761859 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 2712738 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 224642 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 2689468 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 2307978 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 2163750 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 190931 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 113477 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1842674 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1838673 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1693791 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1331580 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 16468 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1143555 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1072819 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6180. Min Range: -8.6180
Max Act: 8.5555. Min Act: -0.1700
Data Index: 1032387 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19