Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5421 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2836. Min Range: -6.2836
Max Act: 6.2836. Min Act: -0.1700
Data Index: 1469619 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2836. Min Range: -6.2836
Max Act: 6.0961. Min Act: -0.1700
Data Index: 3173761 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2836. Min Range: -6.2836
Max Act: 6.0336. Min Act: -0.1700
Data Index: 7302214 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.9711. Min Act: -0.1700
Data Index: 4783984 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2836. Min Range: -6.2836
Max Act: 6.0023. Min Act: -0.1700
Data Index: 7095458 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.9711. Min Act: -0.1700
Data Index: 5823957 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.9398. Min Act: -0.1700
Data Index: 6156247 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.8773. Min Act: -0.1700
Data Index: 633079 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.8461. Min Act: -0.1700
Data Index: 7113502 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.8461. Min Act: -0.1700
Data Index: 7074730 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.8148. Min Act: -0.1700
Data Index: 2552860 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4681418 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7836. Min Act: -0.1700
Data Index: 7074733 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7523. Min Act: -0.1700
Data Index: 4440598 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7523. Min Act: -0.1700
Data Index: 1442456 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7211. Min Act: -0.1700
Data Index: 8162308 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7523. Min Act: -0.1700
Data Index: 1847026 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7523. Min Act: -0.1700
Data Index: 6486838 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.7523. Min Act: -0.1700
Data Index: 673878 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2836. Min Range: -6.2836
Max Act: 5.6898. Min Act: -0.1700
Data Index: 6559440 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19