Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.3856. Min Act: -0.1700
Data Index: 8212682 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.3856. Min Act: -0.1700
Data Index: 1904863 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.3856. Min Act: -0.1700
Data Index: 7872359 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.2377. Min Act: -0.1700
Data Index: 40876 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.2377. Min Act: -0.1700
Data Index: 878139 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.2377. Min Act: -0.1700
Data Index: 6740786 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.2377. Min Act: -0.1700
Data Index: 7007664 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.1880. Min Act: -0.1699
Data Index: 3824437 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.1046. Min Act: -0.1700
Data Index: 2135250 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.1046. Min Act: -0.1700
Data Index: 5184767 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.1046. Min Act: -0.1700
Data Index: 5276746 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0711. Min Act: -0.1700
Data Index: 6737797 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0543. Min Act: -0.1700
Data Index: 2138772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1554
Data Index: 4799351 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1697
Data Index: 5663267 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1700
Data Index: 2292877 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1700
Data Index: 2558549 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1699
Data Index: 6353497 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1613
Data Index: 421398 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3856. Min Range: -2.3856
Max Act: 2.0037. Min Act: -0.1700
Data Index: 6043896 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19