Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 961 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.5594. Min Act: -0.1700
Data Index: 5261364 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.3407. Min Act: -0.1700
Data Index: 7390525 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.3719. Min Act: -0.1700
Data Index: 6706100 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.3407. Min Act: -0.1700
Data Index: 4788136 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.3094. Min Act: -0.1700
Data Index: 821370 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.1844. Min Act: -0.1700
Data Index: 2011799 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.1531. Min Act: -0.1700
Data Index: 1930228 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.1531. Min Act: -0.1700
Data Index: 8149925 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.1531. Min Act: -0.1700
Data Index: 3488865 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0906. Min Act: -0.1700
Data Index: 5340352 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.1219. Min Act: -0.1700
Data Index: 2753473 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0906. Min Act: -0.1700
Data Index: 2834015 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0594. Min Act: -0.1700
Data Index: 376345 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0906. Min Act: -0.1700
Data Index: 2687258 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0281. Min Act: -0.1700
Data Index: 8143257 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0594. Min Act: -0.1700
Data Index: 8261075 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0594. Min Act: -0.1700
Data Index: 7806529 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0594. Min Act: -0.1700
Data Index: 7350443 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5594. Min Range: -4.5594
Max Act: 4.0906. Min Act: -0.1700
Data Index: 4648927 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5594. Min Range: -4.5594
Max Act: 3.9969. Min Act: -0.1700
Data Index: 4826244 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19