Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.4533. Min Act: -0.1700
Data Index: 8473537 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.3908. Min Act: -0.1700
Data Index: 8732751 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.3908. Min Act: -0.1700
Data Index: 8110585 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.3595. Min Act: -0.1700
Data Index: 8197558 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.3283. Min Act: -0.1700
Data Index: 5514493 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.2970. Min Act: -0.1700
Data Index: 1006211 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.2970. Min Act: -0.1700
Data Index: 6965211 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.2658. Min Act: -0.1700
Data Index: 5530103 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.2345. Min Act: -0.1700
Data Index: 1585942 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.2345. Min Act: -0.1700
Data Index: 8221729 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.2345. Min Act: -0.1700
Data Index: 7411695 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1720. Min Act: -0.1700
Data Index: 4118223 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1720. Min Act: -0.1700
Data Index: 3211391 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1720. Min Act: -0.1700
Data Index: 136041 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1720. Min Act: -0.1700
Data Index: 7075781 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1720. Min Act: -0.1700
Data Index: 7551223 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1407. Min Act: -0.1700
Data Index: 2705555 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1407. Min Act: -0.1700
Data Index: 7850730 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.1407. Min Act: -0.1700
Data Index: 7397947 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4533. Min Range: -4.4533
Max Act: 4.0782. Min Act: -0.1700
Data Index: 8093446 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19