Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 487 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1790. Min Range: -5.1790
Max Act: 5.1790. Min Act: -0.1700
Data Index: 8091588 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.8353. Min Act: -0.1700
Data Index: 4947663 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.8353. Min Act: -0.1700
Data Index: 7068741 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.8040. Min Act: -0.1700
Data Index: 4667142 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.7728. Min Act: -0.1700
Data Index: 5509842 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.6478. Min Act: -0.1700
Data Index: 1343618 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.6165. Min Act: -0.1700
Data Index: 4985125 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.6478. Min Act: -0.1700
Data Index: 841076 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.6165. Min Act: -0.1700
Data Index: 801109 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5853. Min Act: -0.1700
Data Index: 7997476 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5540. Min Act: -0.1700
Data Index: 5496501 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5540. Min Act: -0.1700
Data Index: 5712865 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5540. Min Act: -0.1700
Data Index: 3725650 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5228. Min Act: -0.1700
Data Index: 5392293 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5540. Min Act: -0.1700
Data Index: 5712873 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5228. Min Act: -0.1700
Data Index: 833014 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5228. Min Act: -0.1700
Data Index: 5035972 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.5540. Min Act: -0.1700
Data Index: 8538065 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.4915. Min Act: -0.1700
Data Index: 5216892 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1790. Min Range: -5.1790
Max Act: 4.4915. Min Act: -0.1700
Data Index: 1730492 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19