Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1180. Min Range: -7.1180
Max Act: 7.1180. Min Act: -0.1700
Data Index: 7538483 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1180. Min Range: -7.1180
Max Act: 7.0242. Min Act: -0.1700
Data Index: 200779 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.9617. Min Act: -0.1700
Data Index: 8000003 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.9305. Min Act: -0.1700
Data Index: 3503613 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.9305. Min Act: -0.1700
Data Index: 6151852 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.9305. Min Act: -0.1700
Data Index: 4982975 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8992. Min Act: -0.1700
Data Index: 1456082 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.9617. Min Act: -0.1700
Data Index: 5761191 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1949501 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8680. Min Act: -0.1700
Data Index: 4598256 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8367. Min Act: -0.1700
Data Index: 3418947 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8367. Min Act: -0.1700
Data Index: 7543270 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8367. Min Act: -0.1700
Data Index: 2121097 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8367. Min Act: -0.1700
Data Index: 4402151 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8055. Min Act: -0.1700
Data Index: 3052143 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8055. Min Act: -0.1700
Data Index: 5472594 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.8055. Min Act: -0.1700
Data Index: 8479802 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.7430. Min Act: -0.1700
Data Index: 7943014 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.7117. Min Act: -0.1700
Data Index: 1576994 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1180. Min Range: -7.1180
Max Act: 6.6805. Min Act: -0.1700
Data Index: 2147169 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19