Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.4080. Min Act: -0.1700
Data Index: 2887250 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.4080. Min Act: -0.1700
Data Index: 4800115 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.4080. Min Act: -0.1700
Data Index: 2461196 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.4080. Min Act: -0.1700
Data Index: 85736 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3767. Min Act: -0.1700
Data Index: 7500842 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3455. Min Act: -0.1700
Data Index: 5910960 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3767. Min Act: -0.1700
Data Index: 3918861 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3767. Min Act: -0.1700
Data Index: 1574936 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3455. Min Act: -0.1700
Data Index: 7453373 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.2830. Min Act: -0.1700
Data Index: 7049346 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 7713445 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 7607018 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 353188 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 7041517 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 975364 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 653829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 5909467 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 1974156 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.2830. Min Act: -0.1700
Data Index: 5284674 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4080. Min Range: -5.4080
Max Act: 5.2830. Min Act: -0.1700
Data Index: 1761827 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19