Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1425 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7826. Min Act: -0.1700
Data Index: 1520825 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7514. Min Act: -0.1700
Data Index: 7307433 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 4476731 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 1823553 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 6382154 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 5945894 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 5644949 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 5044006 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 4901691 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 4758559 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 8018913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 7766232 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 7336729 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.7201. Min Act: -0.1700
Data Index: 1034787 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.6888. Min Act: -0.1700
Data Index: 4864975 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.6888. Min Act: -0.1700
Data Index: 1730227 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.6888. Min Act: -0.1700
Data Index: 36371 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.6888. Min Act: -0.1700
Data Index: 5303260 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.6888. Min Act: -0.1700
Data Index: 1781957 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7826. Min Range: -3.7826
Max Act: 3.6888. Min Act: -0.1700
Data Index: 304701 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19