Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3653. Min Range: -8.3653
Max Act: 8.3653. Min Act: -0.1700
Data Index: 6422310 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3653. Min Range: -8.3653
Max Act: 7.3965. Min Act: -0.1700
Data Index: 4926546 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3653. Min Range: -8.3653
Max Act: 7.3028. Min Act: -0.1700
Data Index: 6516672 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3653. Min Range: -8.3653
Max Act: 7.2090. Min Act: -0.1700
Data Index: 2154614 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3653. Min Range: -8.3653
Max Act: 7.0528. Min Act: -0.1700
Data Index: 540931 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3653. Min Range: -8.3653
Max Act: 7.0215. Min Act: -0.1700
Data Index: 914334 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.9903. Min Act: -0.1700
Data Index: 7270515 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.8340. Min Act: -0.1700
Data Index: 1371123 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.8028. Min Act: -0.1700
Data Index: 8303242 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.8340. Min Act: -0.1700
Data Index: 6876326 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.8028. Min Act: -0.1700
Data Index: 384702 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.7090. Min Act: -0.1700
Data Index: 6530481 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.7090. Min Act: -0.1700
Data Index: 3319198 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.7403. Min Act: -0.1700
Data Index: 3902429 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.6465. Min Act: -0.1700
Data Index: 8346484 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.6465. Min Act: -0.1700
Data Index: 4082899 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.6778. Min Act: -0.1700
Data Index: 289146 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.6778. Min Act: -0.1700
Data Index: 7651846 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.6153. Min Act: -0.1700
Data Index: 7020069 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3653. Min Range: -8.3653
Max Act: 6.6465. Min Act: -0.1700
Data Index: 3892795 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19