Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3600. Min Range: -8.3600
Max Act: 8.3600. Min Act: -0.1700
Data Index: 2356994 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3600. Min Range: -8.3600
Max Act: 8.3600. Min Act: -0.1700
Data Index: 7529898 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3600. Min Range: -8.3600
Max Act: 8.2975. Min Act: -0.1700
Data Index: 6059916 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3600. Min Range: -8.3600
Max Act: 8.1725. Min Act: -0.1700
Data Index: 1659699 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3600. Min Range: -8.3600
Max Act: 8.0475. Min Act: -0.1700
Data Index: 8739647 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3600. Min Range: -8.3600
Max Act: 8.0475. Min Act: -0.1700
Data Index: 1221867 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.9850. Min Act: -0.1700
Data Index: 5771948 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.9850. Min Act: -0.1700
Data Index: 3319928 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.9850. Min Act: -0.1700
Data Index: 847500 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.9225. Min Act: -0.1700
Data Index: 2578953 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.8600. Min Act: -0.1700
Data Index: 6023722 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.9225. Min Act: -0.1700
Data Index: 5274689 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.8600. Min Act: -0.1700
Data Index: 7100759 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.8600. Min Act: -0.1700
Data Index: 461878 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.8600. Min Act: -0.1700
Data Index: 6988934 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.7975. Min Act: -0.1700
Data Index: 6763722 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.7975. Min Act: -0.1700
Data Index: 3277040 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.7350. Min Act: -0.1700
Data Index: 518777 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.7350. Min Act: -0.1700
Data Index: 934867 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3600. Min Range: -8.3600
Max Act: 7.7350. Min Act: -0.1700
Data Index: 73773 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19