Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2077. Min Range: -7.2077
Max Act: 7.2077. Min Act: -0.1700
Data Index: 2541008 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2077. Min Range: -7.2077
Max Act: 7.0202. Min Act: -0.1700
Data Index: 6833891 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.8952. Min Act: -0.1700
Data Index: 2745673 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.8952. Min Act: -0.1700
Data Index: 3366451 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.8327. Min Act: -0.1700
Data Index: 6138693 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.7390. Min Act: -0.1700
Data Index: 4731312 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.7390. Min Act: -0.1700
Data Index: 6618387 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.7390. Min Act: -0.1700
Data Index: 2707219 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.7077. Min Act: -0.1700
Data Index: 7024574 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.7077. Min Act: -0.1700
Data Index: 5045949 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.7077. Min Act: -0.1700
Data Index: 8412514 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.6765. Min Act: -0.1700
Data Index: 3527045 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.6765. Min Act: -0.1700
Data Index: 1786781 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.6452. Min Act: -0.1700
Data Index: 8018924 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.6452. Min Act: -0.1700
Data Index: 5228122 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.6140. Min Act: -0.1700
Data Index: 3863222 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.5827. Min Act: -0.1700
Data Index: 364836 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.5827. Min Act: -0.1700
Data Index: 1338439 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.5515. Min Act: -0.1700
Data Index: 3263885 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2077. Min Range: -7.2077
Max Act: 6.5515. Min Act: -0.1700
Data Index: 596484 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19