Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4905. Min Range: -9.4905
Max Act: 9.4905. Min Act: -0.1700
Data Index: 4248261 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4905. Min Range: -9.4905
Max Act: 9.2405. Min Act: -0.1700
Data Index: 4725483 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4905. Min Range: -9.4905
Max Act: 9.1155. Min Act: -0.1700
Data Index: 151833 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.7405. Min Act: -0.1700
Data Index: 2881963 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.5530. Min Act: -0.1700
Data Index: 8408557 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.5530. Min Act: -0.1700
Data Index: 5369801 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.3655. Min Act: -0.1700
Data Index: 1084318 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.3655. Min Act: -0.1700
Data Index: 413996 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.3030. Min Act: -0.1700
Data Index: 648573 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.2405. Min Act: -0.1700
Data Index: 3803033 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.2405. Min Act: -0.1700
Data Index: 3454773 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.2405. Min Act: -0.1700
Data Index: 896294 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.1780. Min Act: -0.1700
Data Index: 8344582 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.1155. Min Act: -0.1700
Data Index: 2524395 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.1155. Min Act: -0.1700
Data Index: 937787 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.0530. Min Act: -0.1700
Data Index: 392775 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.0530. Min Act: -0.1700
Data Index: 7424463 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.0530. Min Act: -0.1700
Data Index: 3942146 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.0530. Min Act: -0.1700
Data Index: 1396284 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4905. Min Range: -9.4905
Max Act: 8.0530. Min Act: -0.1700
Data Index: 3748512 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19