Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.6259. Min Act: -0.1700
Data Index: 5471455 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.6172. Min Act: -0.1700
Data Index: 5258716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.6172. Min Act: -0.1700
Data Index: 6061179 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.6085. Min Act: -0.1700
Data Index: 4380162 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5910. Min Act: -0.1700
Data Index: 2548080 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.6172. Min Act: -0.1700
Data Index: 3007430 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5910. Min Act: -0.1700
Data Index: 6416968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5910. Min Act: -0.1700
Data Index: 923174 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5823. Min Act: -0.1698
Data Index: 2748431 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5823. Min Act: -0.1700
Data Index: 6981709 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5910. Min Act: -0.1700
Data Index: 2597493 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5910. Min Act: -0.1700
Data Index: 7268703 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5910. Min Act: -0.1700
Data Index: 7891670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5735. Min Act: -0.1700
Data Index: 1072875 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5823. Min Act: -0.1697
Data Index: 8743164 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5735. Min Act: -0.1700
Data Index: 6887668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5648. Min Act: -0.1700
Data Index: 6268229 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5648. Min Act: -0.1700
Data Index: 4336595 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5648. Min Act: -0.1700
Data Index: 6629865 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6259. Min Range: -1.6259
Max Act: 1.5823. Min Act: -0.1699
Data Index: 189622 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19