Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2687. Min Range: -4.2687
Max Act: 4.2687. Min Act: -0.1700
Data Index: 2011043 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2687. Min Range: -4.2687
Max Act: 4.1437. Min Act: -0.1700
Data Index: 8655451 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2687. Min Range: -4.2687
Max Act: 4.1125. Min Act: -0.1700
Data Index: 8145294 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2687. Min Range: -4.2687
Max Act: 4.0187. Min Act: -0.1700
Data Index: 2131542 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2687. Min Range: -4.2687
Max Act: 4.0500. Min Act: -0.1700
Data Index: 5131788 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9562. Min Act: -0.1700
Data Index: 7987845 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9562. Min Act: -0.1700
Data Index: 3706671 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9562. Min Act: -0.1700
Data Index: 2933934 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9562. Min Act: -0.1700
Data Index: 2009880 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9249. Min Act: -0.1700
Data Index: 7716683 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9249. Min Act: -0.1700
Data Index: 6720331 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9249. Min Act: -0.1700
Data Index: 4290393 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9249. Min Act: -0.1700
Data Index: 4750790 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9249. Min Act: -0.1700
Data Index: 5557931 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.9249. Min Act: -0.1700
Data Index: 3309334 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.8936. Min Act: -0.1700
Data Index: 3345313 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.8936. Min Act: -0.1700
Data Index: 3830894 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.8936. Min Act: -0.1700
Data Index: 8005059 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.8936. Min Act: -0.1700
Data Index: 2518528 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2687. Min Range: -4.2687
Max Act: 3.8936. Min Act: -0.1700
Data Index: 7200497 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19