Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4557 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.4653. Min Act: -0.1700
Data Index: 6430116 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.3403. Min Act: -0.1700
Data Index: 6264255 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.2778. Min Act: -0.1700
Data Index: 5269386 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.3090. Min Act: -0.1700
Data Index: 6845917 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.2465. Min Act: -0.1700
Data Index: 962416 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.2153. Min Act: -0.1700
Data Index: 3066168 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.2465. Min Act: -0.1700
Data Index: 7082752 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.2153. Min Act: -0.1700
Data Index: 5030408 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.1840. Min Act: -0.1700
Data Index: 8060091 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.1528. Min Act: -0.1700
Data Index: 6438859 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.1528. Min Act: -0.1700
Data Index: 2730107 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3872522 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.1215. Min Act: -0.1700
Data Index: 5856326 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.1215. Min Act: -0.1700
Data Index: 206901 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.0903. Min Act: -0.1700
Data Index: 3243245 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.0903. Min Act: -0.1700
Data Index: 8498150 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.0903. Min Act: -0.1700
Data Index: 2247517 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.0903. Min Act: -0.1700
Data Index: 5733510 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.0590. Min Act: -0.1700
Data Index: 3872525 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4653. Min Range: -5.4653
Max Act: 5.0278. Min Act: -0.1700
Data Index: 4286720 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19