Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.6572. Min Act: -0.1700
Data Index: 4712272 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.6572. Min Act: -0.1700
Data Index: 7018188 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.5947. Min Act: -0.1700
Data Index: 989595 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.5322. Min Act: -0.1700
Data Index: 6556823 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.5322. Min Act: -0.1700
Data Index: 5292769 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.4072. Min Act: -0.1700
Data Index: 4619926 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.4072. Min Act: -0.1700
Data Index: 228988 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.4072. Min Act: -0.1700
Data Index: 6492387 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.3447. Min Act: -0.1700
Data Index: 2519502 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.3447. Min Act: -0.1700
Data Index: 2064310 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.2822. Min Act: -0.1700
Data Index: 1129659 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.2197. Min Act: -0.1700
Data Index: 3784561 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.2197. Min Act: -0.1700
Data Index: 1749954 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.2197. Min Act: -0.1700
Data Index: 5878940 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.2197. Min Act: -0.1700
Data Index: 6458882 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.1572. Min Act: -0.1700
Data Index: 6746180 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.2197. Min Act: -0.1700
Data Index: 3903726 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.1572. Min Act: -0.1700
Data Index: 6599904 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.0947. Min Act: -0.1700
Data Index: 6530923 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6572. Min Range: -8.6572
Max Act: 8.1572. Min Act: -0.1700
Data Index: 5632215 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19