Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6141 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3842. Min Range: -9.3842
Max Act: 9.3842. Min Act: -0.1700
Data Index: 2498616 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3842. Min Range: -9.3842
Max Act: 9.3217. Min Act: -0.1700
Data Index: 8126724 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3842. Min Range: -9.3842
Max Act: 9.0717. Min Act: -0.1700
Data Index: 1706933 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 4392921 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 5980829 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 5262035 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 7177596 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 8800847 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 5386321 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 2468304 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 5511639 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 2355879 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8217. Min Act: -0.1700
Data Index: 2498614 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.8842. Min Act: -0.1700
Data Index: 4811096 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 4941466 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 1397533 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 2498615 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 6034657 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 7150603 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3842. Min Range: -9.3842
Max Act: 8.7592. Min Act: -0.1700
Data Index: 1984294 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19