Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.2142. Min Act: -0.1700
Data Index: 2129322 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.2767. Min Act: -0.1700
Data Index: 1715453 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.2142. Min Act: -0.1700
Data Index: 1111770 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.1829. Min Act: -0.1700
Data Index: 8712903 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.0579. Min Act: -0.1700
Data Index: 6977108 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.0579. Min Act: -0.1700
Data Index: 4634491 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.0267. Min Act: -0.1700
Data Index: 8159976 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2767. Min Range: -6.2767
Max Act: 6.0579. Min Act: -0.1700
Data Index: 5135491 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.9954. Min Act: -0.1700
Data Index: 3355703 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.9954. Min Act: -0.1700
Data Index: 442614 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.9954. Min Act: -0.1700
Data Index: 6881614 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.9954. Min Act: -0.1700
Data Index: 2034564 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.9329. Min Act: -0.1700
Data Index: 284666 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.9017. Min Act: -0.1700
Data Index: 4254323 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.8704. Min Act: -0.1700
Data Index: 276976 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.8392. Min Act: -0.1700
Data Index: 8345423 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.8392. Min Act: -0.1700
Data Index: 8285890 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.8392. Min Act: -0.1700
Data Index: 7489368 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.8392. Min Act: -0.1700
Data Index: 7728299 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2767. Min Range: -6.2767
Max Act: 5.8079. Min Act: -0.1700
Data Index: 1265871 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19