Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2655. Min Range: -4.2655
Max Act: 4.2655. Min Act: -0.1700
Data Index: 8062505 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2655. Min Range: -4.2655
Max Act: 4.2030. Min Act: -0.1700
Data Index: 2113568 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2655. Min Range: -4.2655
Max Act: 4.1405. Min Act: -0.1700
Data Index: 6598734 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2655. Min Range: -4.2655
Max Act: 4.1405. Min Act: -0.1700
Data Index: 1229334 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2655. Min Range: -4.2655
Max Act: 4.0155. Min Act: -0.1700
Data Index: 1904015 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9842. Min Act: -0.1700
Data Index: 2586351 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9842. Min Act: -0.1700
Data Index: 8789495 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9842. Min Act: -0.1700
Data Index: 2532529 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9842. Min Act: -0.1700
Data Index: 3533120 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9842. Min Act: -0.1700
Data Index: 7590822 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9217. Min Act: -0.1700
Data Index: 3345501 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9529. Min Act: -0.1700
Data Index: 6225945 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9529. Min Act: -0.1700
Data Index: 8763462 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9217. Min Act: -0.1700
Data Index: 7789830 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9217. Min Act: -0.1700
Data Index: 7162918 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.8904. Min Act: -0.1700
Data Index: 7016713 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.8904. Min Act: -0.1700
Data Index: 8751192 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.9217. Min Act: -0.1700
Data Index: 2394680 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.8904. Min Act: -0.1700
Data Index: 4239739 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2655. Min Range: -4.2655
Max Act: 3.8591. Min Act: -0.1700
Data Index: 1384662 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19