Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.4631. Min Act: -0.1700
Data Index: 6301027 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0881. Min Act: -0.1700
Data Index: 2501464 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0256. Min Act: -0.1700
Data Index: 4116886 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 1756421 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9318. Min Act: -0.1700
Data Index: 4818613 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9318. Min Act: -0.1700
Data Index: 6216623 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 7428904 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9006. Min Act: -0.1700
Data Index: 7911912 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9006. Min Act: -0.1700
Data Index: 1947959 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9006. Min Act: -0.1700
Data Index: 5629176 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 6839642 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 6711141 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8381. Min Act: -0.1700
Data Index: 1876785 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8381. Min Act: -0.1700
Data Index: 1828251 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6315409 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 5574324 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2145849 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8068. Min Act: -0.1700
Data Index: 5433341 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8068. Min Act: -0.1700
Data Index: 1449589 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8068. Min Act: -0.1700
Data Index: 1125942 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19