Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4300 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0686. Min Range: -13.0686
Max Act: 13.0686. Min Act: -0.1700
Data Index: 7356182 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.8186. Min Act: -0.1700
Data Index: 7770539 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.7561. Min Act: -0.1700
Data Index: 1834911 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.6936. Min Act: -0.1700
Data Index: 6944562 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.5686. Min Act: -0.1700
Data Index: 1093262 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.5061. Min Act: -0.1700
Data Index: 2926955 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.3811. Min Act: -0.1700
Data Index: 2313860 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.3811. Min Act: -0.1700
Data Index: 2995886 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.3186. Min Act: -0.1700
Data Index: 11355 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.3811. Min Act: -0.1700
Data Index: 3166070 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.1936. Min Act: -0.1700
Data Index: 3987442 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.2561. Min Act: -0.1700
Data Index: 3552439 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.1936. Min Act: -0.1700
Data Index: 3671780 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.1311. Min Act: -0.1700
Data Index: 4894038 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.1311. Min Act: -0.1700
Data Index: 2273985 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.0686. Min Act: -0.1700
Data Index: 1566140 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.0686. Min Act: -0.1700
Data Index: 956667 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.0061. Min Act: -0.1700
Data Index: 8200771 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0686. Min Range: -13.0686
Max Act: 12.0061. Min Act: -0.1700
Data Index: 2663078 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0686. Min Range: -13.0686
Max Act: 11.8811. Min Act: -0.1700
Data Index: 4377504 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19