Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2416. Min Range: -6.2416
Max Act: 6.2416. Min Act: -0.1700
Data Index: 2091 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2416. Min Range: -6.2416
Max Act: 6.1478. Min Act: -0.1700
Data Index: 8179003 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.8041. Min Act: -0.1700
Data Index: 1312058 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5231531 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.7728. Min Act: -0.1700
Data Index: 4910865 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.6791. Min Act: -0.1700
Data Index: 6723571 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.6791. Min Act: -0.1700
Data Index: 8551149 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.6478. Min Act: -0.1700
Data Index: 1650526 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.6478. Min Act: -0.1700
Data Index: 2208019 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.6166. Min Act: -0.1700
Data Index: 3283951 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5853. Min Act: -0.1700
Data Index: 584504 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3881549 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5853. Min Act: -0.1700
Data Index: 4960130 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5853. Min Act: -0.1700
Data Index: 2864001 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5853. Min Act: -0.1700
Data Index: 2222066 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5541. Min Act: -0.1700
Data Index: 3983033 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5541. Min Act: -0.1700
Data Index: 138143 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5541. Min Act: -0.1700
Data Index: 4105721 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3827675 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2416. Min Range: -6.2416
Max Act: 5.5541. Min Act: -0.1700
Data Index: 2083861 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19