Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.9340. Min Act: -0.1700
Data Index: 2817993 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.5590. Min Act: -0.1700
Data Index: 589844 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.4340. Min Act: -0.1700
Data Index: 5243336 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.2465. Min Act: -0.1700
Data Index: 8057897 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.1840. Min Act: -0.1700
Data Index: 2486876 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.1215. Min Act: -0.1700
Data Index: 7590430 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.1215. Min Act: -0.1700
Data Index: 3054772 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.1215. Min Act: -0.1700
Data Index: 2268728 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.0590. Min Act: -0.1700
Data Index: 6651160 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.0590. Min Act: -0.1700
Data Index: 1226167 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.0590. Min Act: -0.1700
Data Index: 8724850 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9340. Min Range: -8.9340
Max Act: 8.0590. Min Act: -0.1700
Data Index: 3996877 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.9340. Min Act: -0.1700
Data Index: 3896439 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.9340. Min Act: -0.1700
Data Index: 740479 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.9027. Min Act: -0.1700
Data Index: 3222099 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.9027. Min Act: -0.1700
Data Index: 7565149 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.9027. Min Act: -0.1700
Data Index: 816509 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.9027. Min Act: -0.1700
Data Index: 600370 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.8715. Min Act: -0.1700
Data Index: 4242475 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9340. Min Range: -8.9340
Max Act: 7.8090. Min Act: -0.1700
Data Index: 1920064 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19