Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0517. Min Range: -8.0517
Max Act: 8.0517. Min Act: -0.1700
Data Index: 1710492 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.9892. Min Act: -0.1700
Data Index: 5077424 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.9892. Min Act: -0.1700
Data Index: 3976774 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.8642. Min Act: -0.1700
Data Index: 4476095 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.8017. Min Act: -0.1700
Data Index: 2112372 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.8017. Min Act: -0.1700
Data Index: 5445642 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.8017. Min Act: -0.1700
Data Index: 3982895 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.8017. Min Act: -0.1700
Data Index: 4810732 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.6767. Min Act: -0.1700
Data Index: 1911640 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.6767. Min Act: -0.1700
Data Index: 1282623 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5829. Min Act: -0.1700
Data Index: 1663856 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5829. Min Act: -0.1700
Data Index: 95828 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5829. Min Act: -0.1700
Data Index: 1767208 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5517. Min Act: -0.1700
Data Index: 5803352 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5517. Min Act: -0.1700
Data Index: 5480192 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5517. Min Act: -0.1700
Data Index: 2223661 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5517. Min Act: -0.1700
Data Index: 7079617 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5517. Min Act: -0.1700
Data Index: 3521545 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.5517. Min Act: -0.1700
Data Index: 1492883 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0517. Min Range: -8.0517
Max Act: 7.4892. Min Act: -0.1700
Data Index: 4382313 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19