Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.9010. Min Act: -0.1700
Data Index: 289286 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.8057. Min Act: -0.1700
Data Index: 4115088 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.8057. Min Act: -0.1700
Data Index: 5971989 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.8057. Min Act: -0.1700
Data Index: 7523171 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.8057. Min Act: -0.1700
Data Index: 854743 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7579. Min Act: -0.1700
Data Index: 3314242 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7898. Min Act: -0.1700
Data Index: 1170106 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7898. Min Act: -0.1700
Data Index: 7844345 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7738. Min Act: -0.1700
Data Index: 6442000 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.8057. Min Act: -0.1700
Data Index: 171702 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7738. Min Act: -0.1700
Data Index: 3339494 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7738. Min Act: -0.1700
Data Index: 3163616 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7419. Min Act: -0.1700
Data Index: 5553624 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7579. Min Act: -0.1700
Data Index: 6531178 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7419. Min Act: -0.1700
Data Index: 7995808 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7579. Min Act: -0.1700
Data Index: 7331073 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7579. Min Act: -0.1700
Data Index: 4155967 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7898. Min Act: -0.1700
Data Index: 5430014 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7738. Min Act: -0.1700
Data Index: 8731724 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9010. Min Range: -2.9010
Max Act: 2.7419. Min Act: -0.1700
Data Index: 3732289 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19