Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.7172. Min Act: -0.1700
Data Index: 6956839 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.7172. Min Act: -0.1700
Data Index: 8117889 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.7172. Min Act: -0.1700
Data Index: 5639914 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6860. Min Act: -0.1700
Data Index: 5656598 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 8274124 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5922. Min Act: -0.1700
Data Index: 8419766 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5922. Min Act: -0.1700
Data Index: 3958045 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5610. Min Act: -0.1700
Data Index: 1486360 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5610. Min Act: -0.1700
Data Index: 8635265 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5297. Min Act: -0.1700
Data Index: 6036001 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5297. Min Act: -0.1700
Data Index: 2981226 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5297. Min Act: -0.1700
Data Index: 3128746 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4985. Min Act: -0.1700
Data Index: 2572516 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4985. Min Act: -0.1700
Data Index: 3290299 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4985. Min Act: -0.1700
Data Index: 3974484 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5297. Min Act: -0.1700
Data Index: 6089002 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4672. Min Act: -0.1700
Data Index: 3711154 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4672. Min Act: -0.1700
Data Index: 2321634 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4672. Min Act: -0.1700
Data Index: 6267856 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.4672. Min Act: -0.1700
Data Index: 8111525 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19