Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3979. Min Range: -8.3979
Max Act: 8.3979. Min Act: -0.1700
Data Index: 8117799 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3979. Min Range: -8.3979
Max Act: 8.0854. Min Act: -0.1700
Data Index: 467519 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.9917. Min Act: -0.1700
Data Index: 6418275 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.8979. Min Act: -0.1700
Data Index: 6300876 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.7104. Min Act: -0.1700
Data Index: 1571256 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.7417. Min Act: -0.1700
Data Index: 4639727 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6792. Min Act: -0.1700
Data Index: 804523 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6792. Min Act: -0.1700
Data Index: 2787270 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6792. Min Act: -0.1700
Data Index: 400825 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6167. Min Act: -0.1700
Data Index: 6089553 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6479. Min Act: -0.1700
Data Index: 719481 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6479. Min Act: -0.1700
Data Index: 7478652 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.6479. Min Act: -0.1700
Data Index: 4114880 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.5854. Min Act: -0.1700
Data Index: 6973283 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.5854. Min Act: -0.1700
Data Index: 5022116 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.5229. Min Act: -0.1700
Data Index: 4686293 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.5229. Min Act: -0.1700
Data Index: 1671992 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.5542. Min Act: -0.1700
Data Index: 8208434 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.5229. Min Act: -0.1700
Data Index: 6375319 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3979. Min Range: -8.3979
Max Act: 7.4917. Min Act: -0.1700
Data Index: 3929239 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19