Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5168 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.8389. Min Act: -0.1700
Data Index: 6140159 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.8076. Min Act: -0.1700
Data Index: 282313 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.7764. Min Act: -0.1700
Data Index: 5609405 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.7764. Min Act: -0.1700
Data Index: 8558282 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.7451. Min Act: -0.1700
Data Index: 4966941 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6825. Min Act: -0.1700
Data Index: 2833124 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6825. Min Act: -0.1700
Data Index: 5772146 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6825. Min Act: -0.1700
Data Index: 4211313 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6512. Min Act: -0.1700
Data Index: 1093932 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6512. Min Act: -0.1700
Data Index: 5904537 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6512. Min Act: -0.1700
Data Index: 2211102 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6199. Min Act: -0.1700
Data Index: 8589745 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 6340755 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.6199. Min Act: -0.1700
Data Index: 2598957 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 5386211 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 7546503 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 8341605 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 3253973 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 591681 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8389. Min Range: -3.8389
Max Act: 3.5886. Min Act: -0.1700
Data Index: 5537434 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19