Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.7661. Min Act: -0.1700
Data Index: 1310917 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.7661. Min Act: -0.1700
Data Index: 5361225 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.7035. Min Act: -0.1700
Data Index: 5748155 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.6098. Min Act: -0.1700
Data Index: 4494928 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.6098. Min Act: -0.1700
Data Index: 8758540 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.5473. Min Act: -0.1700
Data Index: 4303032 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.5160. Min Act: -0.1700
Data Index: 6958688 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.5160. Min Act: -0.1700
Data Index: 2424640 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.5160. Min Act: -0.1700
Data Index: 2796662 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4848. Min Act: -0.1700
Data Index: 1744682 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4535. Min Act: -0.1700
Data Index: 5361228 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4535. Min Act: -0.1700
Data Index: 6422771 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3816865 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.3910. Min Act: -0.1700
Data Index: 2752024 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.3910. Min Act: -0.1700
Data Index: 3534594 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4223. Min Act: -0.1700
Data Index: 6474619 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4223. Min Act: -0.1700
Data Index: 5361243 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.4223. Min Act: -0.1700
Data Index: 5361236 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.3910. Min Act: -0.1700
Data Index: 236196 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7661. Min Range: -4.7661
Max Act: 4.3910. Min Act: -0.1700
Data Index: 2456678 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19