Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4799 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.9141. Min Act: -0.1700
Data Index: 4010110 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8828. Min Act: -0.1700
Data Index: 8242359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8516. Min Act: -0.1700
Data Index: 6688171 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8516. Min Act: -0.1700
Data Index: 5268368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8516. Min Act: -0.1700
Data Index: 6517788 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8516. Min Act: -0.1700
Data Index: 90713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 7943347 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8203. Min Act: -0.1700
Data Index: 8171766 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8203. Min Act: -0.1700
Data Index: 1403635 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8203. Min Act: -0.1700
Data Index: 1756991 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8203. Min Act: -0.1700
Data Index: 5417096 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8203. Min Act: -0.1700
Data Index: 5499226 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.8203. Min Act: -0.1700
Data Index: 6055274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 6553479 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 6341341 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 567936 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 6039896 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1699
Data Index: 5290528 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 244798 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9141. Min Range: -3.9141
Max Act: 3.7890. Min Act: -0.1700
Data Index: 4995916 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19