Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1552. Min Range: -4.1552
Max Act: 4.1552. Min Act: -0.1700
Data Index: 1678411 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9676. Min Act: -0.1700
Data Index: 5310425 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9676. Min Act: -0.1700
Data Index: 7188857 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9676. Min Act: -0.1700
Data Index: 4580300 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9051. Min Act: -0.1700
Data Index: 1726946 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9051. Min Act: -0.1700
Data Index: 8726891 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9051. Min Act: -0.1700
Data Index: 5737484 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.9051. Min Act: -0.1700
Data Index: 1958911 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8738. Min Act: -0.1700
Data Index: 5857199 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6758672 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8425. Min Act: -0.1700
Data Index: 1844894 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.7800. Min Act: -0.1700
Data Index: 1749353 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8113. Min Act: -0.1700
Data Index: 239066 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8425. Min Act: -0.1700
Data Index: 8036660 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8113. Min Act: -0.1700
Data Index: 5367726 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8113. Min Act: -0.1700
Data Index: 2197366 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.8113. Min Act: -0.1700
Data Index: 947632 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.7487. Min Act: -0.1700
Data Index: 2088598 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.7800. Min Act: -0.1700
Data Index: 92356 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1552. Min Range: -4.1552
Max Act: 3.7800. Min Act: -0.1700
Data Index: 6279679 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19