Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0810. Min Range: -6.0810
Max Act: 6.0810. Min Act: -0.1700
Data Index: 543366 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.9248. Min Act: -0.1700
Data Index: 7616052 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.9560. Min Act: -0.1699
Data Index: 7676526 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.9248. Min Act: -0.1700
Data Index: 4433555 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.8310. Min Act: -0.1700
Data Index: 2346933 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7998. Min Act: -0.1700
Data Index: 6521172 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7998. Min Act: -0.1700
Data Index: 4919273 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.8310. Min Act: -0.1700
Data Index: 7676523 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1902906 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7685. Min Act: -0.1700
Data Index: 979965 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7685. Min Act: -0.1700
Data Index: 4675115 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7373. Min Act: -0.1700
Data Index: 8667251 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7373. Min Act: -0.1700
Data Index: 5801227 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5681546 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5968730 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.6748. Min Act: -0.1700
Data Index: 5720932 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.7060. Min Act: -0.1700
Data Index: 7201787 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.6748. Min Act: -0.1700
Data Index: 1854776 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.6748. Min Act: -0.1700
Data Index: 7234777 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0810. Min Range: -6.0810
Max Act: 5.6435. Min Act: -0.1700
Data Index: 4341017 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19