Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.9939. Min Act: -0.1700
Data Index: 5794075 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.6189. Min Act: -0.1700
Data Index: 2518458 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.5564. Min Act: -0.1700
Data Index: 1331550 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.3689. Min Act: -0.1700
Data Index: 5115082 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.2439. Min Act: -0.1700
Data Index: 2661858 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.0564. Min Act: -0.1700
Data Index: 7362443 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9939. Min Range: -8.9939
Max Act: 8.0252. Min Act: -0.1700
Data Index: 2808079 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.9939. Min Act: -0.1700
Data Index: 53874 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.9627. Min Act: -0.1700
Data Index: 6096522 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.9314. Min Act: -0.1700
Data Index: 7957722 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.9314. Min Act: -0.1700
Data Index: 6743887 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.9002. Min Act: -0.1700
Data Index: 7848631 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.9002. Min Act: -0.1700
Data Index: 6126915 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.8377. Min Act: -0.1700
Data Index: 4961535 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.8377. Min Act: -0.1700
Data Index: 4809570 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.8064. Min Act: -0.1700
Data Index: 4698051 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.8064. Min Act: -0.1700
Data Index: 3773738 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.7752. Min Act: -0.1700
Data Index: 2518459 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.7439. Min Act: -0.1700
Data Index: 8616560 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9939. Min Range: -8.9939
Max Act: 7.7127. Min Act: -0.1700
Data Index: 5601972 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19