Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7142. Min Range: -10.7142
Max Act: 10.7142. Min Act: -0.1700
Data Index: 2369764 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7142. Min Range: -10.7142
Max Act: 10.2767. Min Act: -0.1700
Data Index: 5709870 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7142. Min Range: -10.7142
Max Act: 10.0892. Min Act: -0.1700
Data Index: 5996749 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7142. Min Range: -10.7142
Max Act: 10.0267. Min Act: -0.1700
Data Index: 2859755 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7142. Min Range: -10.7142
Max Act: 10.0267. Min Act: -0.1700
Data Index: 8641935 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7142. Min Range: -10.7142
Max Act: 10.0267. Min Act: -0.1700
Data Index: 4189050 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.9642. Min Act: -0.1700
Data Index: 4476102 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.8392. Min Act: -0.1700
Data Index: 27384 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.9017. Min Act: -0.1700
Data Index: 8241449 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.8392. Min Act: -0.1700
Data Index: 5271609 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.9017. Min Act: -0.1700
Data Index: 4002461 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.7767. Min Act: -0.1700
Data Index: 5073369 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.7142. Min Act: -0.1700
Data Index: 7251701 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.7142. Min Act: -0.1700
Data Index: 6597406 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.7142. Min Act: -0.1700
Data Index: 4704513 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.6517. Min Act: -0.1700
Data Index: 1861627 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.7142. Min Act: -0.1700
Data Index: 3211644 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.6517. Min Act: -0.1700
Data Index: 6352816 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.6517. Min Act: -0.1700
Data Index: 7329891 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7142. Min Range: -10.7142
Max Act: 9.6517. Min Act: -0.1700
Data Index: 709214 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19