Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.5852. Min Act: -0.1700
Data Index: 5658652 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.3665. Min Act: -0.1700
Data Index: 7803085 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.3665. Min Act: -0.1700
Data Index: 5822997 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.3352. Min Act: -0.1700
Data Index: 4171174 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.3352. Min Act: -0.1700
Data Index: 2449076 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.3040. Min Act: -0.1700
Data Index: 2824947 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 4512460 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 2353472 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 4177974 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 639352 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 2197502 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 4688018 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2727. Min Act: -0.1700
Data Index: 5691026 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2415. Min Act: -0.1700
Data Index: 705854 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2415. Min Act: -0.1700
Data Index: 2456162 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2415. Min Act: -0.1700
Data Index: 3078107 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2415. Min Act: -0.1700
Data Index: 1637667 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.1789. Min Act: -0.1700
Data Index: 7919539 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.2102. Min Act: -0.1700
Data Index: 4348375 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5852. Min Range: -4.5852
Max Act: 4.1477. Min Act: -0.1700
Data Index: 3060233 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19