Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1160 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0590. Min Range: -12.0590
Max Act: 12.0590. Min Act: -0.1700
Data Index: 78757 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.9340. Min Act: -0.1700
Data Index: 911359 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.9340. Min Act: -0.1700
Data Index: 7256103 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.4965. Min Act: -0.1700
Data Index: 7342770 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.3715. Min Act: -0.1700
Data Index: 6095369 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.3715. Min Act: -0.1700
Data Index: 4821805 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.3090. Min Act: -0.1700
Data Index: 932233 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.2465. Min Act: -0.1700
Data Index: 6480566 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1840. Min Act: -0.1700
Data Index: 1991317 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1840. Min Act: -0.1700
Data Index: 6194806 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1215. Min Act: -0.1700
Data Index: 1965706 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1215. Min Act: -0.1700
Data Index: 1274959 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1215. Min Act: -0.1700
Data Index: 3148969 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1215. Min Act: -0.1700
Data Index: 4289427 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.1215. Min Act: -0.1700
Data Index: 6419066 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.0590. Min Act: -0.1700
Data Index: 5097218 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.0590. Min Act: -0.1700
Data Index: 2945074 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0590. Min Range: -12.0590
Max Act: 10.9965. Min Act: -0.1700
Data Index: 2247955 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0590. Min Range: -12.0590
Max Act: 11.0590. Min Act: -0.1700
Data Index: 454751 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0590. Min Range: -12.0590
Max Act: 10.9965. Min Act: -0.1700
Data Index: 6745344 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19