Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 223 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.3165. Min Act: -0.1700
Data Index: 3765149 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.1915. Min Act: -0.1700
Data Index: 5876272 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0352. Min Act: -0.1700
Data Index: 6239714 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0352. Min Act: -0.1700
Data Index: 1099149 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0352. Min Act: -0.1700
Data Index: 6667576 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3165. Min Range: -7.3165
Max Act: 7.0040. Min Act: -0.1700
Data Index: 6960489 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.9415. Min Act: -0.1700
Data Index: 89338 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8790. Min Act: -0.1700
Data Index: 1855280 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8790. Min Act: -0.1700
Data Index: 563062 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.9102. Min Act: -0.1700
Data Index: 2169560 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8790. Min Act: -0.1700
Data Index: 1900959 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8790. Min Act: -0.1700
Data Index: 6721068 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8477. Min Act: -0.1700
Data Index: 3199510 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8477. Min Act: -0.1700
Data Index: 4356420 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8477. Min Act: -0.1700
Data Index: 96487 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8165. Min Act: -0.1700
Data Index: 1536635 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8165. Min Act: -0.1700
Data Index: 4982377 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8165. Min Act: -0.1700
Data Index: 5175610 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.7852. Min Act: -0.1700
Data Index: 2532972 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3165. Min Range: -7.3165
Max Act: 6.8165. Min Act: -0.1700
Data Index: 3402241 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19