Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.6982. Min Act: -0.1700
Data Index: 1277597 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6982. Min Range: -7.6982
Max Act: 7.3544. Min Act: -0.1700
Data Index: 3291473 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.9794. Min Act: -0.1700
Data Index: 4723324 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.8857. Min Act: -0.1700
Data Index: 4227379 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.8857. Min Act: -0.1700
Data Index: 6916258 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7919. Min Act: -0.1700
Data Index: 711796 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7919. Min Act: -0.1700
Data Index: 3541009 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7919. Min Act: -0.1700
Data Index: 5524949 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7919. Min Act: -0.1700
Data Index: 6698545 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7607. Min Act: -0.1700
Data Index: 6994123 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7294. Min Act: -0.1700
Data Index: 2001043 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7294. Min Act: -0.1700
Data Index: 2546807 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.7607. Min Act: -0.1700
Data Index: 8538874 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.6357. Min Act: -0.1700
Data Index: 6500050 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.6669. Min Act: -0.1700
Data Index: 1726090 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.6357. Min Act: -0.1700
Data Index: 6976627 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.6357. Min Act: -0.1700
Data Index: 3335895 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.6044. Min Act: -0.1700
Data Index: 5076839 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.6044. Min Act: -0.1700
Data Index: 7973969 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6982. Min Range: -7.6982
Max Act: 6.5732. Min Act: -0.1700
Data Index: 6861202 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19