Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.3923. Min Act: -0.1700
Data Index: 4364592 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.2985. Min Act: -0.1700
Data Index: 4769619 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.0798. Min Act: -0.1700
Data Index: 7717771 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.1110. Min Act: -0.1700
Data Index: 4607578 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.0798. Min Act: -0.1700
Data Index: 1459760 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.0798. Min Act: -0.1700
Data Index: 1003321 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.0173. Min Act: -0.1700
Data Index: 7387069 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.0173. Min Act: -0.1700
Data Index: 4161437 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3923. Min Range: -7.3923
Max Act: 7.0173. Min Act: -0.1700
Data Index: 5958259 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.9860. Min Act: -0.1700
Data Index: 5232349 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.9860. Min Act: -0.1700
Data Index: 4076600 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.9860. Min Act: -0.1700
Data Index: 3016757 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.9548. Min Act: -0.1700
Data Index: 5339273 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.9235. Min Act: -0.1700
Data Index: 1894471 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.9235. Min Act: -0.1700
Data Index: 3597855 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.8923. Min Act: -0.1700
Data Index: 8482686 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.8610. Min Act: -0.1700
Data Index: 2316978 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.8923. Min Act: -0.1700
Data Index: 3723987 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.8923. Min Act: -0.1700
Data Index: 2041396 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3923. Min Range: -7.3923
Max Act: 6.8610. Min Act: -0.1700
Data Index: 5614958 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19