Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.6827. Min Act: -0.1700
Data Index: 3539791 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.6202. Min Act: -0.1700
Data Index: 4788295 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4952. Min Act: -0.1700
Data Index: 2782722 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4327. Min Act: -0.1700
Data Index: 8379000 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4327. Min Act: -0.1700
Data Index: 3502550 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4952. Min Act: -0.1700
Data Index: 2827038 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4327. Min Act: -0.1700
Data Index: 4157905 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4327. Min Act: -0.1700
Data Index: 3823058 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.4327. Min Act: -0.1700
Data Index: 8130729 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.3077. Min Act: -0.1700
Data Index: 5910832 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.3702. Min Act: -0.1700
Data Index: 2781362 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.3702. Min Act: -0.1700
Data Index: 5782144 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.3702. Min Act: -0.1700
Data Index: 1021477 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.2452. Min Act: -0.1700
Data Index: 8301655 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.2452. Min Act: -0.1700
Data Index: 4679043 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.2452. Min Act: -0.1700
Data Index: 8090518 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.3077. Min Act: -0.1700
Data Index: 4892573 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.3077. Min Act: -0.1700
Data Index: 7618123 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.2452. Min Act: -0.1700
Data Index: 4823419 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6827. Min Range: -8.6827
Max Act: 8.2452. Min Act: -0.1700
Data Index: 6219719 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19