Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.4502. Min Act: -0.1700
Data Index: 4419809 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.3252. Min Act: -0.1700
Data Index: 7419112 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.2627. Min Act: -0.1700
Data Index: 980195 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.2627. Min Act: -0.1700
Data Index: 5839661 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.2002. Min Act: -0.1700
Data Index: 415400 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.2002. Min Act: -0.1700
Data Index: 5638213 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.1377. Min Act: -0.1700
Data Index: 7744461 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0752. Min Act: -0.1700
Data Index: 113018 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.1377. Min Act: -0.1700
Data Index: 2294990 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0752. Min Act: -0.1700
Data Index: 2084332 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0752. Min Act: -0.1700
Data Index: 2084331 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0752. Min Act: -0.1700
Data Index: 418073 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0752. Min Act: -0.1700
Data Index: 7399630 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0127. Min Act: -0.1700
Data Index: 2623560 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0127. Min Act: -0.1700
Data Index: 5922875 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4502. Min Range: -9.4502
Max Act: 9.0127. Min Act: -0.1700
Data Index: 5200546 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4502. Min Range: -9.4502
Max Act: 8.9502. Min Act: -0.1700
Data Index: 4648203 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4502. Min Range: -9.4502
Max Act: 8.9502. Min Act: -0.1700
Data Index: 4521214 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4502. Min Range: -9.4502
Max Act: 8.9502. Min Act: -0.1700
Data Index: 547963 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4502. Min Range: -9.4502
Max Act: 8.8877. Min Act: -0.1700
Data Index: 1699873 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19