Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0752. Min Range: -9.0752
Max Act: 9.0752. Min Act: -0.1700
Data Index: 5537700 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.8252. Min Act: -0.1700
Data Index: 3352358 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.7002. Min Act: -0.1700
Data Index: 2878229 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.6377. Min Act: -0.1700
Data Index: 1273710 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.6377. Min Act: -0.1700
Data Index: 3448631 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.6377. Min Act: -0.1700
Data Index: 513749 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.5752. Min Act: -0.1700
Data Index: 2252285 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.5752. Min Act: -0.1700
Data Index: 899579 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.5752. Min Act: -0.1700
Data Index: 7102652 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.5752. Min Act: -0.1700
Data Index: 2781504 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.5127. Min Act: -0.1700
Data Index: 3044855 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.4502. Min Act: -0.1700
Data Index: 8054422 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.4502. Min Act: -0.1700
Data Index: 8280644 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.4502. Min Act: -0.1700
Data Index: 4038539 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.3877. Min Act: -0.1700
Data Index: 7382258 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.4502. Min Act: -0.1700
Data Index: 959712 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.4502. Min Act: -0.1700
Data Index: 3078086 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.3877. Min Act: -0.1700
Data Index: 81498 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.3877. Min Act: -0.1700
Data Index: 4988930 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0752. Min Range: -9.0752
Max Act: 8.3252. Min Act: -0.1700
Data Index: 2151806 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19