Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 814 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.9623. Min Act: -0.1700
Data Index: 6952311 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.8373. Min Act: -0.1700
Data Index: 6495779 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.8373. Min Act: -0.1700
Data Index: 4659137 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.6498. Min Act: -0.1700
Data Index: 4680999 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.5560. Min Act: -0.1700
Data Index: 75800 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.5560. Min Act: -0.1700
Data Index: 5480216 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.5248. Min Act: -0.1700
Data Index: 6585385 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.5560. Min Act: -0.1700
Data Index: 7163694 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3818144 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3781151 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4935. Min Act: -0.1700
Data Index: 1847834 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4935. Min Act: -0.1700
Data Index: 593047 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4935. Min Act: -0.1700
Data Index: 6530895 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4935. Min Act: -0.1700
Data Index: 4192408 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4935. Min Act: -0.1700
Data Index: 1708409 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4623. Min Act: -0.1700
Data Index: 2368511 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4623. Min Act: -0.1700
Data Index: 1813521 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4623. Min Act: -0.1700
Data Index: 7491355 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4623. Min Act: -0.1700
Data Index: 4990917 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9623. Min Range: -5.9623
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3169545 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19