Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5672 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.8646. Min Act: -0.1700
Data Index: 6102866 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7708. Min Act: -0.1700
Data Index: 6018273 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7396. Min Act: -0.1700
Data Index: 7005768 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7396. Min Act: -0.1700
Data Index: 2417932 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7396. Min Act: -0.1700
Data Index: 2019354 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7083. Min Act: -0.1699
Data Index: 2998082 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7083. Min Act: -0.1700
Data Index: 795663 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7083. Min Act: -0.1700
Data Index: 5476086 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7083. Min Act: -0.1700
Data Index: 5970835 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.7083. Min Act: -0.1700
Data Index: 6524441 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6771. Min Act: -0.1700
Data Index: 1311488 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4442855 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6458. Min Act: -0.1700
Data Index: 6906252 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6458. Min Act: -0.1700
Data Index: 2190297 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6458. Min Act: -0.1700
Data Index: 271678 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6458. Min Act: -0.1700
Data Index: 272333 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6146. Min Act: -0.1700
Data Index: 3445614 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6703335 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6681100 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8646. Min Range: -5.8646
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6563467 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19