Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4563 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1471. Min Range: -9.1471
Max Act: 9.1471. Min Act: -0.1700
Data Index: 4733907 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.9596. Min Act: -0.1700
Data Index: 2612791 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.9596. Min Act: -0.1700
Data Index: 5475299 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.9596. Min Act: -0.1700
Data Index: 2612779 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.8971. Min Act: -0.1700
Data Index: 8509292 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.8971. Min Act: -0.1700
Data Index: 8338068 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.8971. Min Act: -0.1700
Data Index: 8509302 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.8346. Min Act: -0.1700
Data Index: 932043 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.8346. Min Act: -0.1700
Data Index: 927756 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.8346. Min Act: -0.1700
Data Index: 2355591 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7721. Min Act: -0.1700
Data Index: 8513897 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7721. Min Act: -0.1700
Data Index: 3895920 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7721. Min Act: -0.1700
Data Index: 512338 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 5472972 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 932024 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 2227497 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 5830142 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 2286387 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 2708432 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1471. Min Range: -9.1471
Max Act: 8.7096. Min Act: -0.1700
Data Index: 2355592 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19