Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0056. Min Range: -8.0056
Max Act: 8.0056. Min Act: -0.1700
Data Index: 7018865 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.6931. Min Act: -0.1700
Data Index: 4853483 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.5994. Min Act: -0.1700
Data Index: 722336 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.5681. Min Act: -0.1700
Data Index: 1855475 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.4431. Min Act: -0.1700
Data Index: 8375216 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.3806. Min Act: -0.1700
Data Index: 8777834 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.3806. Min Act: -0.1700
Data Index: 4265067 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.3806. Min Act: -0.1700
Data Index: 591406 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.4119. Min Act: -0.1700
Data Index: 2070803 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.3494. Min Act: -0.1700
Data Index: 6746809 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2869. Min Act: -0.1700
Data Index: 2189945 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.3494. Min Act: -0.1700
Data Index: 4264566 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2869. Min Act: -0.1700
Data Index: 7154544 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2556. Min Act: -0.1700
Data Index: 7985658 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2244. Min Act: -0.1700
Data Index: 2683503 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2244. Min Act: -0.1700
Data Index: 999600 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.2244. Min Act: -0.1700
Data Index: 8692913 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.1931. Min Act: -0.1700
Data Index: 6811374 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.1931. Min Act: -0.1700
Data Index: 8343027 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0056. Min Range: -8.0056
Max Act: 7.1619. Min Act: -0.1700
Data Index: 2125281 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19