Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.3190. Min Act: -0.1700
Data Index: 5136584 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.2252. Min Act: -0.1700
Data Index: 4615745 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.2565. Min Act: -0.1700
Data Index: 4615735 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.1315. Min Act: -0.1700
Data Index: 5563008 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.1002. Min Act: -0.1700
Data Index: 8075095 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.0377. Min Act: -0.1700
Data Index: 5136582 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.0065. Min Act: -0.1700
Data Index: 4935122 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3190. Min Range: -7.3190
Max Act: 7.0065. Min Act: -0.1700
Data Index: 5199523 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.9127. Min Act: -0.1700
Data Index: 7469746 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.9440. Min Act: -0.1700
Data Index: 5136585 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.9440. Min Act: -0.1700
Data Index: 5136583 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.9440. Min Act: -0.1700
Data Index: 4615738 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.9127. Min Act: -0.1700
Data Index: 8112773 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.9127. Min Act: -0.1700
Data Index: 4935129 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.8502. Min Act: -0.1700
Data Index: 5134685 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2525091 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2750324 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.8502. Min Act: -0.1700
Data Index: 6603068 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.8502. Min Act: -0.1700
Data Index: 4935109 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3190. Min Range: -7.3190
Max Act: 6.8190. Min Act: -0.1700
Data Index: 1796298 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19