Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6186 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0503. Min Range: -7.0503
Max Act: 7.0503. Min Act: -0.1700
Data Index: 355056 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0503. Min Range: -7.0503
Max Act: 7.0190. Min Act: -0.1700
Data Index: 4081822 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0503. Min Range: -7.0503
Max Act: 7.0190. Min Act: -0.1700
Data Index: 4743554 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0503. Min Range: -7.0503
Max Act: 7.0190. Min Act: -0.1700
Data Index: 7117071 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 7889306 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 8566405 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 863738 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 8502448 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 8412602 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 3901977 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 2748602 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 518883 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 7030945 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 6216533 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9878. Min Act: -0.1700
Data Index: 5943710 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9565. Min Act: -0.1700
Data Index: 3309455 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9565. Min Act: -0.1700
Data Index: 1090459 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9565. Min Act: -0.1700
Data Index: 3744140 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9565. Min Act: -0.1700
Data Index: 3894812 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0503. Min Range: -7.0503
Max Act: 6.9565. Min Act: -0.1700
Data Index: 38356 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19