Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1573 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.6519. Min Act: -0.1700
Data Index: 6162226 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.6206. Min Act: -0.1700
Data Index: 4368069 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7767286 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.6206. Min Act: -0.1700
Data Index: 4014772 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5894. Min Act: -0.1700
Data Index: 4313418 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5894. Min Act: -0.1700
Data Index: 962969 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5894. Min Act: -0.1700
Data Index: 8026647 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5894. Min Act: -0.1700
Data Index: 4957129 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5894. Min Act: -0.1700
Data Index: 552368 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 4242925 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 4889344 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 675128 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 3291448 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 6569661 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5269. Min Act: -0.1700
Data Index: 8603746 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 6547258 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 8377553 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5269. Min Act: -0.1700
Data Index: 7585646 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.5581. Min Act: -0.1700
Data Index: 39520 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6519. Min Range: -4.6519
Max Act: 4.4956. Min Act: -0.1700
Data Index: 7845240 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19