Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.7936. Min Act: -0.1700
Data Index: 6976417 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.7623. Min Act: -0.1700
Data Index: 4870306 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.7311. Min Act: -0.1700
Data Index: 1184274 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.6686. Min Act: -0.1700
Data Index: 1854644 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.6373. Min Act: -0.1700
Data Index: 29711 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.6061. Min Act: -0.1700
Data Index: 3287800 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.4811. Min Act: -0.1700
Data Index: 4496854 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.4811. Min Act: -0.1700
Data Index: 8593473 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.3873. Min Act: -0.1700
Data Index: 942715 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.3561. Min Act: -0.1700
Data Index: 8444344 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.3248. Min Act: -0.1700
Data Index: 3578758 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 4999837 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 700881 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 168366 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 3490196 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 7835336 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 7725279 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2623. Min Act: -0.1700
Data Index: 3925578 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2623. Min Act: -0.1700
Data Index: 4381778 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7936. Min Range: -6.7936
Max Act: 6.2623. Min Act: -0.1700
Data Index: 3936627 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19