Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.6017. Min Act: -0.1700
Data Index: 5377391 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.4767. Min Act: -0.1700
Data Index: 8406927 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.3517. Min Act: -0.1700
Data Index: 835917 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.2892. Min Act: -0.1700
Data Index: 1890059 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.2892. Min Act: -0.1700
Data Index: 4257419 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.2267. Min Act: -0.1700
Data Index: 8391287 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.2267. Min Act: -0.1700
Data Index: 4695572 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.2267. Min Act: -0.1700
Data Index: 1887016 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.1017. Min Act: -0.1700
Data Index: 2369765 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6017. Min Range: -9.6017
Max Act: 9.0392. Min Act: -0.1700
Data Index: 4254805 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.9767. Min Act: -0.1700
Data Index: 8007479 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.9142. Min Act: -0.1700
Data Index: 7137747 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.9142. Min Act: -0.1700
Data Index: 8450071 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.8517. Min Act: -0.1700
Data Index: 2566272 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.8517. Min Act: -0.1700
Data Index: 7464260 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.8517. Min Act: -0.1700
Data Index: 4160840 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.7892. Min Act: -0.1700
Data Index: 3780155 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.7892. Min Act: -0.1700
Data Index: 1120520 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.7892. Min Act: -0.1700
Data Index: 4160842 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6017. Min Range: -9.6017
Max Act: 8.7267. Min Act: -0.1700
Data Index: 2149771 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19