Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4346 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.3815. Min Act: -0.1700
Data Index: 6385002 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1940. Min Act: -0.1700
Data Index: 6384996 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1940. Min Act: -0.1700
Data Index: 713408 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1315. Min Act: -0.1700
Data Index: 7597306 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1002. Min Act: -0.1700
Data Index: 623300 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1002. Min Act: -0.1700
Data Index: 839426 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1002. Min Act: -0.1700
Data Index: 8551578 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.1002. Min Act: -0.1700
Data Index: 8323737 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.0065. Min Act: -0.1700
Data Index: 6500627 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3815. Min Range: -6.3815
Max Act: 6.0065. Min Act: -0.1700
Data Index: 7417152 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.9752. Min Act: -0.1700
Data Index: 1293990 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.9440. Min Act: -0.1700
Data Index: 2268933 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.9127. Min Act: -0.1700
Data Index: 6978724 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.9440. Min Act: -0.1700
Data Index: 5470567 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.9127. Min Act: -0.1700
Data Index: 4134239 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.8815. Min Act: -0.1700
Data Index: 6711116 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.8815. Min Act: -0.1700
Data Index: 6191673 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.8815. Min Act: -0.1700
Data Index: 660253 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.8815. Min Act: -0.1700
Data Index: 127492 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3815. Min Range: -6.3815
Max Act: 5.8815. Min Act: -0.1700
Data Index: 6706783 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19