Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 195 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.3051. Min Act: -0.1700
Data Index: 987257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.3051. Min Act: -0.1700
Data Index: 2279365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2737. Min Act: -0.1700
Data Index: 2947496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2737. Min Act: -0.1700
Data Index: 7323831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2737. Min Act: -0.1700
Data Index: 2356231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2580. Min Act: -0.1700
Data Index: 3388092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2422. Min Act: -0.1700
Data Index: 5488398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2422. Min Act: -0.1700
Data Index: 6708204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2422. Min Act: -0.1700
Data Index: 7029305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2422. Min Act: -0.1700
Data Index: 3048913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2422. Min Act: -0.1700
Data Index: 3130805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2265. Min Act: -0.1700
Data Index: 4852634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2265. Min Act: -0.1700
Data Index: 5280274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2265. Min Act: -0.1700
Data Index: 3700960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.2265. Min Act: -0.1700
Data Index: 971781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.1951. Min Act: -0.1700
Data Index: 1693174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.1794. Min Act: -0.1700
Data Index: 7129416 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.0691. Min Act: -0.1700
Data Index: 1480402 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.0849. Min Act: -0.1700
Data Index: 4105945 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3051. Min Range: -3.3051
Max Act: 3.0691. Min Act: -0.1700
Data Index: 8115183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19