Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0397. Min Range: -6.0397
Max Act: 6.0397. Min Act: -0.1700
Data Index: 879941 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.8209. Min Act: -0.1700
Data Index: 1454362 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6959. Min Act: -0.1700
Data Index: 6681995 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.7272. Min Act: -0.1700
Data Index: 2327129 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4658277 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8273573 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6334. Min Act: -0.1700
Data Index: 5286265 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6022. Min Act: -0.1700
Data Index: 5876243 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6022. Min Act: -0.1700
Data Index: 6917873 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5770067 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.6022. Min Act: -0.1700
Data Index: 8456842 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5709. Min Act: -0.1700
Data Index: 4839640 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5709. Min Act: -0.1700
Data Index: 2777441 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5709. Min Act: -0.1700
Data Index: 8268333 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5946522 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5397. Min Act: -0.1700
Data Index: 1075447 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4704346 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5084. Min Act: -0.1700
Data Index: 5413341 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5084. Min Act: -0.1700
Data Index: 225600 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0397. Min Range: -6.0397
Max Act: 5.5084. Min Act: -0.1700
Data Index: 7691836 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19