Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.3412. Min Act: -0.1700
Data Index: 3323922 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.3099. Min Act: -0.1700
Data Index: 5442859 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.2787. Min Act: -0.1700
Data Index: 749763 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.2474. Min Act: -0.1700
Data Index: 3265583 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.1849. Min Act: -0.1700
Data Index: 60667 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.1849. Min Act: -0.1700
Data Index: 4239127 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.1224. Min Act: -0.1700
Data Index: 2114210 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.1224. Min Act: -0.1700
Data Index: 7930077 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3412. Min Range: -6.3412
Max Act: 6.0599. Min Act: -0.1700
Data Index: 542471 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7189726 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9349. Min Act: -0.1700
Data Index: 5975704 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9349. Min Act: -0.1700
Data Index: 5720924 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9037. Min Act: -0.1700
Data Index: 372070 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9037. Min Act: -0.1700
Data Index: 7662823 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9037. Min Act: -0.1700
Data Index: 1949133 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.9037. Min Act: -0.1700
Data Index: 2063686 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.8724. Min Act: -0.1700
Data Index: 5557252 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.8412. Min Act: -0.1700
Data Index: 3124752 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.8412. Min Act: -0.1700
Data Index: 6218458 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3412. Min Range: -6.3412
Max Act: 5.8412. Min Act: -0.1700
Data Index: 5752087 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19