Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4372 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3528. Min Range: -6.3528
Max Act: 6.3528. Min Act: -0.1700
Data Index: 2204923 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3528. Min Range: -6.3528
Max Act: 6.1653. Min Act: -0.1700
Data Index: 600782 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.9153. Min Act: -0.1700
Data Index: 8576137 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.8215. Min Act: -0.1700
Data Index: 3587801 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.8215. Min Act: -0.1700
Data Index: 5412509 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.7590. Min Act: -0.1700
Data Index: 8363591 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.7278. Min Act: -0.1700
Data Index: 2993625 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6965. Min Act: -0.1700
Data Index: 1496840 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6965. Min Act: -0.1700
Data Index: 531452 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6653. Min Act: -0.1700
Data Index: 5256368 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6965. Min Act: -0.1700
Data Index: 2813388 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6340. Min Act: -0.1700
Data Index: 8421402 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6340. Min Act: -0.1700
Data Index: 2817035 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.6340. Min Act: -0.1700
Data Index: 5192682 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.5715. Min Act: -0.1700
Data Index: 3812530 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.5715. Min Act: -0.1700
Data Index: 1129459 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.5715. Min Act: -0.1700
Data Index: 3173113 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.5403. Min Act: -0.1700
Data Index: 509434 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.5403. Min Act: -0.1700
Data Index: 2195071 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3528. Min Range: -6.3528
Max Act: 5.5090. Min Act: -0.1700
Data Index: 4796071 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19