Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 496 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.4943. Min Act: -0.1700
Data Index: 3701987 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.5030. Min Act: -0.1700
Data Index: 7346777 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.5030. Min Act: -0.1700
Data Index: 872851 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.4855. Min Act: -0.1700
Data Index: 2141128 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.4679. Min Act: -0.1700
Data Index: 8327810 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.4063. Min Act: -0.1700
Data Index: 2525896 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3975. Min Act: -0.1700
Data Index: 4777444 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3887. Min Act: -0.1700
Data Index: 481032 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3887. Min Act: -0.1700
Data Index: 5237788 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3799. Min Act: -0.1700
Data Index: 5112160 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3711. Min Act: -0.1700
Data Index: 5237786 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3711. Min Act: -0.1700
Data Index: 2687568 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3711. Min Act: -0.1700
Data Index: 8636906 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3622. Min Act: -0.1700
Data Index: 3598739 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3534. Min Act: -0.1700
Data Index: 6635325 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3534. Min Act: -0.1700
Data Index: 5136932 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3446. Min Act: -0.1700
Data Index: 1258144 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3446. Min Act: -0.1700
Data Index: 3833069 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3534. Min Act: -0.1700
Data Index: 702258 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5030. Min Range: -1.5030
Max Act: 1.3358. Min Act: -0.1700
Data Index: 6979312 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19