Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.6780. Min Act: -0.1700
Data Index: 3312463 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.6155. Min Act: -0.1700
Data Index: 1355246 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.5843. Min Act: -0.1699
Data Index: 3300816 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.4905. Min Act: -0.1699
Data Index: 2064666 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.4905. Min Act: -0.1700
Data Index: 1368547 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.4593. Min Act: -0.1700
Data Index: 2987486 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.4280. Min Act: -0.1700
Data Index: 3690274 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3968. Min Act: -0.1700
Data Index: 60445 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3968. Min Act: -0.1700
Data Index: 3329973 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3655. Min Act: -0.1700
Data Index: 3107991 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3968. Min Act: -0.1700
Data Index: 7949771 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3030. Min Act: -0.1700
Data Index: 8374565 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3030. Min Act: -0.1700
Data Index: 8760936 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3030. Min Act: -0.1700
Data Index: 894033 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3030. Min Act: -0.1700
Data Index: 1198199 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3030. Min Act: -0.1700
Data Index: 6167845 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.2718. Min Act: -0.1700
Data Index: 4474999 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.2718. Min Act: -0.1700
Data Index: 7048105 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.2718. Min Act: -0.1700
Data Index: 4538829 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6780. Min Range: -5.6780
Max Act: 5.3030. Min Act: -0.1700
Data Index: 7379037 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19