Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.7725. Min Act: -0.1700
Data Index: 8585106 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6787. Min Act: -0.1700
Data Index: 2690985 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6475. Min Act: -0.1700
Data Index: 1731634 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6787. Min Act: -0.1700
Data Index: 1932079 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6475. Min Act: -0.1700
Data Index: 8764174 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6475. Min Act: -0.1700
Data Index: 8205548 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6475. Min Act: -0.1700
Data Index: 4687517 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6162. Min Act: -0.1700
Data Index: 5888950 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6162. Min Act: -0.1700
Data Index: 7562770 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6162. Min Act: -0.1700
Data Index: 6823673 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6162. Min Act: -0.1700
Data Index: 4963466 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 3294859 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6162. Min Act: -0.1700
Data Index: 145253 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 7613662 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5537. Min Act: -0.1700
Data Index: 3112088 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 1384942 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 2147668 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5537. Min Act: -0.1700
Data Index: 5068395 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5537. Min Act: -0.1700
Data Index: 6552600 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5225. Min Act: -0.1700
Data Index: 5655691 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19