Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.8718. Min Act: -0.1700
Data Index: 7140841 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.7605. Min Act: -0.1700
Data Index: 820097 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.6965. Min Act: -0.1700
Data Index: 7030016 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.6485. Min Act: -0.1700
Data Index: 2834614 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.6485. Min Act: -0.1700
Data Index: 7778802 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.6324. Min Act: -0.1700
Data Index: 2015535 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.6163. Min Act: -0.1700
Data Index: 820099 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.6002. Min Act: -0.1700
Data Index: 765592 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5841. Min Act: -0.1700
Data Index: 3038041 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5841. Min Act: -0.1700
Data Index: 820098 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5519. Min Act: -0.1700
Data Index: 3539498 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5357. Min Act: -0.1700
Data Index: 4707949 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5357. Min Act: -0.1700
Data Index: 8471667 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5196. Min Act: -0.1700
Data Index: 286392 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5196. Min Act: -0.1700
Data Index: 5556011 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5034. Min Act: -0.1700
Data Index: 5726396 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5196. Min Act: -0.1700
Data Index: 5726411 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5034. Min Act: -0.1700
Data Index: 5726400 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.5034. Min Act: -0.1700
Data Index: 2811020 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8718. Min Range: -2.8718
Max Act: 2.4872. Min Act: -0.1700
Data Index: 5726397 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19