Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1495. Min Range: -5.1495
Max Act: 5.1495. Min Act: -0.1700
Data Index: 579393 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1495. Min Range: -5.1495
Max Act: 5.0245. Min Act: -0.1700
Data Index: 5355895 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1495. Min Range: -5.1495
Max Act: 5.0245. Min Act: -0.1700
Data Index: 7362339 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.9933. Min Act: -0.1700
Data Index: 7391876 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.9620. Min Act: -0.1700
Data Index: 1832953 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.9308. Min Act: -0.1700
Data Index: 2989071 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.9620. Min Act: -0.1700
Data Index: 5369373 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8995. Min Act: -0.1700
Data Index: 2128489 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.9308. Min Act: -0.1700
Data Index: 1880680 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8995. Min Act: -0.1700
Data Index: 7944822 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8683. Min Act: -0.1700
Data Index: 7047188 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8683. Min Act: -0.1700
Data Index: 2189001 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8683. Min Act: -0.1700
Data Index: 7594856 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8058. Min Act: -0.1700
Data Index: 2084913 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8683. Min Act: -0.1700
Data Index: 2320866 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8683. Min Act: -0.1700
Data Index: 2128486 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8058. Min Act: -0.1700
Data Index: 4696858 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.7433. Min Act: -0.1700
Data Index: 3177817 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.7745. Min Act: -0.1700
Data Index: 3322282 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1495. Min Range: -5.1495
Max Act: 4.8058. Min Act: -0.1700
Data Index: 2185033 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19