Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0752. Min Range: -8.0752
Max Act: 8.0752. Min Act: -0.1700
Data Index: 8731395 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.9502. Min Act: -0.1700
Data Index: 1185079 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.7002. Min Act: -0.1700
Data Index: 3166087 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.7002. Min Act: -0.1700
Data Index: 1560707 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.7002. Min Act: -0.1700
Data Index: 1560708 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.6377. Min Act: -0.1700
Data Index: 5745792 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.5752. Min Act: -0.1700
Data Index: 894184 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.5440. Min Act: -0.1700
Data Index: 1820048 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.3565. Min Act: -0.1700
Data Index: 2233096 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.3565. Min Act: -0.1700
Data Index: 8788429 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2940. Min Act: -0.1700
Data Index: 4748585 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2940. Min Act: -0.1700
Data Index: 3680666 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2940. Min Act: -0.1700
Data Index: 2042915 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2315. Min Act: -0.1700
Data Index: 6443746 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2315. Min Act: -0.1700
Data Index: 3944100 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2627. Min Act: -0.1700
Data Index: 7590826 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2002. Min Act: -0.1700
Data Index: 6090787 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2315. Min Act: -0.1700
Data Index: 3388231 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2315. Min Act: -0.1700
Data Index: 1708718 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0752. Min Range: -8.0752
Max Act: 7.2315. Min Act: -0.1700
Data Index: 8267612 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19