Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5321 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.9811. Min Act: -0.1700
Data Index: 6671991 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.6686. Min Act: -0.1700
Data Index: 3776317 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.6373. Min Act: -0.1700
Data Index: 12957 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.5748. Min Act: -0.1700
Data Index: 6746317 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.5123. Min Act: -0.1700
Data Index: 2471218 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.4498. Min Act: -0.1700
Data Index: 7995640 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.4186. Min Act: -0.1700
Data Index: 6171334 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.4498. Min Act: -0.1700
Data Index: 4272009 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.4186. Min Act: -0.1700
Data Index: 7094632 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.4498. Min Act: -0.1700
Data Index: 82695 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.4186. Min Act: -0.1700
Data Index: 2037083 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3873. Min Act: -0.1700
Data Index: 7723736 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3873. Min Act: -0.1700
Data Index: 7261941 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3561. Min Act: -0.1700
Data Index: 4994693 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3873. Min Act: -0.1700
Data Index: 5307636 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3873. Min Act: -0.1700
Data Index: 5448960 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3561. Min Act: -0.1700
Data Index: 5081775 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3248. Min Act: -0.1700
Data Index: 2713187 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3248. Min Act: -0.1700
Data Index: 420288 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9811. Min Range: -6.9811
Max Act: 6.3248. Min Act: -0.1700
Data Index: 5978673 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19