Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.8581. Min Act: -0.1700
Data Index: 6884258 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.6081. Min Act: -0.1700
Data Index: 5447555 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.4206. Min Act: -0.1700
Data Index: 2497709 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.2956. Min Act: -0.1700
Data Index: 2603344 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.1706. Min Act: -0.1700
Data Index: 7092456 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.1081. Min Act: -0.1700
Data Index: 7790683 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.1081. Min Act: -0.1700
Data Index: 7850945 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9831. Min Act: -0.1700
Data Index: 2701226 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8581. Min Range: -8.8581
Max Act: 8.0456. Min Act: -0.1700
Data Index: 7083079 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9831. Min Act: -0.1700
Data Index: 5756246 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9831. Min Act: -0.1700
Data Index: 4317740 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9831. Min Act: -0.1700
Data Index: 1499677 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9206. Min Act: -0.1700
Data Index: 2125086 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9206. Min Act: -0.1700
Data Index: 5481700 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.9206. Min Act: -0.1700
Data Index: 7391485 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.8581. Min Act: -0.1700
Data Index: 476026 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.8581. Min Act: -0.1700
Data Index: 2903302 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.7956. Min Act: -0.1700
Data Index: 6758319 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.7956. Min Act: -0.1700
Data Index: 1990826 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8581. Min Range: -8.8581
Max Act: 7.8581. Min Act: -0.1700
Data Index: 3207689 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19