Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.4899. Min Act: -0.1700
Data Index: 5634760 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.3649. Min Act: -0.1700
Data Index: 4077870 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.2399. Min Act: -0.1700
Data Index: 512636 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.2399. Min Act: -0.1700
Data Index: 4077868 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.2086. Min Act: -0.1700
Data Index: 1129336 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.1774. Min Act: -0.1700
Data Index: 7934969 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.1774. Min Act: -0.1700
Data Index: 782502 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.1461. Min Act: -0.1700
Data Index: 512633 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.1774. Min Act: -0.1700
Data Index: 1608804 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.1149. Min Act: -0.1700
Data Index: 4304033 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.0836. Min Act: -0.1700
Data Index: 4304036 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.0524. Min Act: -0.1700
Data Index: 512632 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.0211. Min Act: -0.1700
Data Index: 7763780 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.0524. Min Act: -0.1700
Data Index: 8710112 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.0211. Min Act: -0.1700
Data Index: 3001916 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4899. Min Range: -5.4899
Max Act: 5.0211. Min Act: -0.1700
Data Index: 4077867 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4899. Min Range: -5.4899
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5152750 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4899. Min Range: -5.4899
Max Act: 4.9899. Min Act: -0.1700
Data Index: 2270453 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4899. Min Range: -5.4899
Max Act: 4.9899. Min Act: -0.1700
Data Index: 1230490 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4899. Min Range: -5.4899
Max Act: 4.9899. Min Act: -0.1700
Data Index: 1013779 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19