Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.4493. Min Act: -0.1700
Data Index: 6141083 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.3243. Min Act: -0.1700
Data Index: 8762000 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.2931. Min Act: -0.1700
Data Index: 6732851 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.2618. Min Act: -0.1700
Data Index: 3666500 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.2306. Min Act: -0.1700
Data Index: 7026080 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.2306. Min Act: -0.1700
Data Index: 7137511 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1681. Min Act: -0.1700
Data Index: 8543640 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1681. Min Act: -0.1700
Data Index: 3472926 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1368. Min Act: -0.1700
Data Index: 1007967 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1368. Min Act: -0.1700
Data Index: 3084077 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1056. Min Act: -0.1700
Data Index: 905925 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1056. Min Act: -0.1700
Data Index: 4333041 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.1056. Min Act: -0.1700
Data Index: 3107903 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0743. Min Act: -0.1700
Data Index: 1783769 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0431. Min Act: -0.1700
Data Index: 5210544 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0743. Min Act: -0.1700
Data Index: 5132122 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0431. Min Act: -0.1700
Data Index: 2783132 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0431. Min Act: -0.1700
Data Index: 539143 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0118. Min Act: -0.1700
Data Index: 823859 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4493. Min Range: -7.4493
Max Act: 7.0118. Min Act: -0.1700
Data Index: 1118721 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19