Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6255 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0590. Min Range: -8.0590
Max Act: 8.0590. Min Act: -0.1700
Data Index: 5029475 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0590. Min Range: -8.0590
Max Act: 8.0590. Min Act: -0.1698
Data Index: 8769470 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9965. Min Act: -0.1700
Data Index: 6619624 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9965. Min Act: -0.1700
Data Index: 6090099 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 2062824 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 4839005 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 4711097 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 5879116 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 788350 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 8499694 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.9340. Min Act: -0.1700
Data Index: 4205387 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 5581930 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 1807273 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 4465400 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8090. Min Act: -0.1700
Data Index: 5978944 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 2144450 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 4529206 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 3685570 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 4205385 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0590. Min Range: -8.0590
Max Act: 7.8715. Min Act: -0.1700
Data Index: 4205386 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19