Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5617 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.7870. Min Act: -0.1700
Data Index: 5596133 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.1620. Min Act: -0.1700
Data Index: 1520750 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.5058. Min Act: -0.1700
Data Index: 1511695 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.4433. Min Act: -0.1700
Data Index: 8122118 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.4433. Min Act: -0.1700
Data Index: 5001594 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.4120. Min Act: -0.1700
Data Index: 1444177 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.3495. Min Act: -0.1700
Data Index: 4276623 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2870. Min Act: -0.1700
Data Index: 7177426 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.3183. Min Act: -0.1700
Data Index: 5139232 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2870. Min Act: -0.1700
Data Index: 62679 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2870. Min Act: -0.1700
Data Index: 7047611 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2558. Min Act: -0.1700
Data Index: 7522761 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2558. Min Act: -0.1700
Data Index: 3212750 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2245. Min Act: -0.1700
Data Index: 5341533 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2245. Min Act: -0.1700
Data Index: 2914919 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.1933. Min Act: -0.1700
Data Index: 7664241 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2558. Min Act: -0.1700
Data Index: 6383386 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2245. Min Act: -0.1700
Data Index: 4402441 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.2558. Min Act: -0.1700
Data Index: 3950849 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7870. Min Range: -8.7870
Max Act: 7.1933. Min Act: -0.1700
Data Index: 8625291 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19