Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 868 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8747. Min Act: -0.1700
Data Index: 7851872 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8747. Min Act: -0.1700
Data Index: 1370644 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8405. Min Act: -0.1700
Data Index: 809118 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8405. Min Act: -0.1700
Data Index: 3352638 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8233. Min Act: -0.1700
Data Index: 3242493 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.8061. Min Act: -0.1700
Data Index: 8539417 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7889. Min Act: -0.1700
Data Index: 5220725 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7889. Min Act: -0.1700
Data Index: 4126154 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7717. Min Act: -0.1700
Data Index: 4649055 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7889. Min Act: -0.1700
Data Index: 2691251 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7717. Min Act: -0.1700
Data Index: 1099173 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7717. Min Act: -0.1700
Data Index: 3144420 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7717. Min Act: -0.1700
Data Index: 2273678 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7544. Min Act: -0.1700
Data Index: 5202645 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7717. Min Act: -0.1700
Data Index: 7590655 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7717. Min Act: -0.1700
Data Index: 6532938 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7544. Min Act: -0.1700
Data Index: 1173355 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7544. Min Act: -0.1700
Data Index: 2314813 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7544. Min Act: -0.1700
Data Index: 2947431 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8747. Min Range: -1.8747
Max Act: 1.7544. Min Act: -0.1700
Data Index: 2275879 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19