Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1750. Min Range: -12.1750
Max Act: 12.1750. Min Act: -0.1700
Data Index: 7577790 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1750. Min Range: -12.1750
Max Act: 12.1125. Min Act: -0.1700
Data Index: 5584271 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1750. Min Range: -12.1750
Max Act: 12.0500. Min Act: -0.1700
Data Index: 7511346 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1750. Min Range: -12.1750
Max Act: 12.0500. Min Act: -0.1700
Data Index: 1960216 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.9875. Min Act: -0.1700
Data Index: 6860216 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.9250. Min Act: -0.1700
Data Index: 8340691 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.8625. Min Act: -0.1700
Data Index: 172266 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.8000. Min Act: -0.1700
Data Index: 4564807 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.7375. Min Act: -0.1700
Data Index: 3928687 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.6750. Min Act: -0.1700
Data Index: 4564813 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.6125. Min Act: -0.1700
Data Index: 5161260 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.6750. Min Act: -0.1700
Data Index: 4106484 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.5500. Min Act: -0.1700
Data Index: 4564806 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.5500. Min Act: -0.1700
Data Index: 8033538 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.6125. Min Act: -0.1700
Data Index: 994764 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.4250. Min Act: -0.1700
Data Index: 2861454 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.4875. Min Act: -0.1700
Data Index: 5548581 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.4875. Min Act: -0.1700
Data Index: 3378330 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.4250. Min Act: -0.1700
Data Index: 8595337 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1750. Min Range: -12.1750
Max Act: 11.4875. Min Act: -0.1700
Data Index: 691527 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19