Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.3077. Min Act: -0.1700
Data Index: 218422 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2764. Min Act: -0.1700
Data Index: 7992067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2764. Min Act: -0.1700
Data Index: 6148067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2452. Min Act: -0.1700
Data Index: 5833999 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2452. Min Act: -0.1700
Data Index: 2761262 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2452. Min Act: -0.1700
Data Index: 1888245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2452. Min Act: -0.1700
Data Index: 5200999 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2139. Min Act: -0.1700
Data Index: 6101894 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2139. Min Act: -0.1700
Data Index: 1882701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 1644532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2139. Min Act: -0.1700
Data Index: 2329974 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 1069272 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2139. Min Act: -0.1700
Data Index: 1211629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.2139. Min Act: -0.1700
Data Index: 1391139 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 1715549 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 936785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 440115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 2617311 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 1194766 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3077. Min Range: -4.3077
Max Act: 4.1827. Min Act: -0.1700
Data Index: 2845416 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19