Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5774 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.7633. Min Act: -0.1700
Data Index: 1165113 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.7320. Min Act: -0.1700
Data Index: 699591 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.7008. Min Act: -0.1700
Data Index: 748487 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.7008. Min Act: -0.1700
Data Index: 873973 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 8189171 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 2842165 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6072533 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6942081 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6383. Min Act: -0.1700
Data Index: 4529480 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 8459568 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6070. Min Act: -0.1700
Data Index: 3135304 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6070. Min Act: -0.1700
Data Index: 448587 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 5265089 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 7802537 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 3913622 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5445. Min Act: -0.1700
Data Index: 5463161 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 448586 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 1313388 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.6070. Min Act: -0.1700
Data Index: 3628373 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7633. Min Range: -6.7633
Max Act: 6.5758. Min Act: -0.1700
Data Index: 8723848 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19