Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 875 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 3910154 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 3458023 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 2732735 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 2607564 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 2534373 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 8108247 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 7964764 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 7940748 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7523. Min Act: -0.1700
Data Index: 7698555 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 7675372 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 329363 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 6520141 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 5799097 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7523. Min Act: -0.1700
Data Index: 4070263 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7836. Min Act: -0.1700
Data Index: 3594314 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7523. Min Act: -0.1700
Data Index: 766045 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7523. Min Act: -0.1700
Data Index: 2667085 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7523. Min Act: -0.1700
Data Index: 2969174 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7523. Min Act: -0.1700
Data Index: 3145334 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7836. Min Range: -3.7836
Max Act: 3.7210. Min Act: -0.1700
Data Index: 3587069 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19