Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.3108. Min Act: -0.1700
Data Index: 2608672 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.1233. Min Act: -0.1700
Data Index: 3250983 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 3536931 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.0608. Min Act: -0.1700
Data Index: 3609083 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.0608. Min Act: -0.1700
Data Index: 495033 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.0608. Min Act: -0.1700
Data Index: 4682420 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.0608. Min Act: -0.1700
Data Index: 4234368 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 2293026 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 1442476 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3108. Min Range: -8.3108
Max Act: 8.0608. Min Act: -0.1700
Data Index: 8057920 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 1006356 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9983. Min Act: -0.1700
Data Index: 2686291 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9670. Min Act: -0.1700
Data Index: 7062770 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9358. Min Act: -0.1700
Data Index: 1568345 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9358. Min Act: -0.1700
Data Index: 2577539 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9358. Min Act: -0.1700
Data Index: 56029 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9358. Min Act: -0.1700
Data Index: 2203555 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.9045. Min Act: -0.1700
Data Index: 2784157 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.8733. Min Act: -0.1700
Data Index: 5417867 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3108. Min Range: -8.3108
Max Act: 7.8733. Min Act: -0.1700
Data Index: 3347165 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19