Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5728 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2584. Min Range: -6.2584
Max Act: 6.2584. Min Act: -0.1700
Data Index: 8104020 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2584. Min Range: -6.2584
Max Act: 6.1959. Min Act: -0.1700
Data Index: 6462530 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.9459. Min Act: -0.1700
Data Index: 738756 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.8834. Min Act: -0.1700
Data Index: 1412838 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.8209. Min Act: -0.1700
Data Index: 6084524 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.6959. Min Act: -0.1700
Data Index: 8296355 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.6647. Min Act: -0.1700
Data Index: 837131 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.6647. Min Act: -0.1700
Data Index: 583616 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.6022. Min Act: -0.1700
Data Index: 6710214 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5709. Min Act: -0.1700
Data Index: 4949867 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5709. Min Act: -0.1700
Data Index: 6545194 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5709. Min Act: -0.1700
Data Index: 8475973 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5709. Min Act: -0.1700
Data Index: 1173523 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5397. Min Act: -0.1700
Data Index: 3267918 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5397. Min Act: -0.1700
Data Index: 3516415 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5397. Min Act: -0.1700
Data Index: 4190032 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5084. Min Act: -0.1700
Data Index: 1766281 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.5084. Min Act: -0.1700
Data Index: 3133796 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.4772. Min Act: -0.1700
Data Index: 7739640 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2584. Min Range: -6.2584
Max Act: 5.4772. Min Act: -0.1700
Data Index: 5713463 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19