Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0602. Min Range: -1.0602
Max Act: 1.0602. Min Act: -0.1700
Data Index: 3048980 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0602. Min Range: -1.0602
Max Act: 1.0079. Min Act: -0.1700
Data Index: 7169078 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0602. Min Range: -1.0602
Max Act: 1.0079. Min Act: -0.1700
Data Index: 715461 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0602. Min Range: -1.0602
Max Act: 1.0079. Min Act: -0.1700
Data Index: 8523023 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9906. Min Act: -0.1699
Data Index: 4882779 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9733. Min Act: -0.1700
Data Index: 1923241 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9733. Min Act: -0.1700
Data Index: 2737319 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9733. Min Act: -0.1700
Data Index: 4528611 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1700
Data Index: 1923231 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1700
Data Index: 895062 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1699
Data Index: 2733063 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1700
Data Index: 4988492 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1700
Data Index: 1665344 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1700
Data Index: 4882781 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9560. Min Act: -0.1700
Data Index: 4882777 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9387. Min Act: -0.1696
Data Index: 3307718 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9387. Min Act: -0.1700
Data Index: 2917331 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9387. Min Act: -0.1700
Data Index: 3330190 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9216. Min Act: -0.1700
Data Index: 2736408 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0602. Min Range: -1.0602
Max Act: 0.9044. Min Act: -0.1700
Data Index: 565014 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19