Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5503 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.9045. Min Act: -0.1700
Data Index: 6531884 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.7795. Min Act: -0.1700
Data Index: 6531883 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.7482. Min Act: -0.1700
Data Index: 2048257 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.4670. Min Act: -0.1700
Data Index: 6531881 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.1232. Min Act: -0.1700
Data Index: 4670884 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.0920. Min Act: -0.1700
Data Index: 6053403 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.0607. Min Act: -0.1700
Data Index: 2408339 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9045. Min Range: -7.9045
Max Act: 7.0295. Min Act: -0.1700
Data Index: 4905623 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.9982. Min Act: -0.1700
Data Index: 3553820 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.9670. Min Act: -0.1700
Data Index: 4373752 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.9670. Min Act: -0.1700
Data Index: 6553876 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.9670. Min Act: -0.1700
Data Index: 4696517 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.9045. Min Act: -0.1700
Data Index: 6152947 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.8732. Min Act: -0.1700
Data Index: 882272 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.8732. Min Act: -0.1700
Data Index: 5118175 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.8420. Min Act: -0.1700
Data Index: 437030 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.8420. Min Act: -0.1700
Data Index: 3136948 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.8420. Min Act: -0.1700
Data Index: 4905252 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.8420. Min Act: -0.1700
Data Index: 5068587 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9045. Min Range: -7.9045
Max Act: 6.7482. Min Act: -0.1700
Data Index: 2777996 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19