Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6036 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.3337. Min Act: -0.1700
Data Index: 8459727 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.3337. Min Act: -0.1700
Data Index: 7009948 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.2087. Min Act: -0.1700
Data Index: 1978098 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.1775. Min Act: -0.1700
Data Index: 972151 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.2087. Min Act: -0.1700
Data Index: 681886 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0525. Min Act: -0.1700
Data Index: 8113262 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0525. Min Act: -0.1700
Data Index: 2779807 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0525. Min Act: -0.1700
Data Index: 1377794 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0212. Min Act: -0.1700
Data Index: 4419574 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0212. Min Act: -0.1700
Data Index: 5804914 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0212. Min Act: -0.1700
Data Index: 1860809 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.9900. Min Act: -0.1700
Data Index: 6934103 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.9900. Min Act: -0.1700
Data Index: 4241047 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3337. Min Range: -5.3337
Max Act: 5.0212. Min Act: -0.1700
Data Index: 4218978 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.9900. Min Act: -0.1700
Data Index: 8554223 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.9587. Min Act: -0.1700
Data Index: 1791724 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.9587. Min Act: -0.1700
Data Index: 5915058 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.9275. Min Act: -0.1700
Data Index: 6225789 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.8962. Min Act: -0.1700
Data Index: 5344422 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3337. Min Range: -5.3337
Max Act: 4.8962. Min Act: -0.1700
Data Index: 3953232 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19