Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2185 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2284985 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2521282 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4450. Min Act: -0.1700
Data Index: 5720688 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4450. Min Act: -0.1700
Data Index: 6855174 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 4306587 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 7591444 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.4138. Min Act: -0.1700
Data Index: 2089922 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3825. Min Act: -0.1700
Data Index: 3795392 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3825. Min Act: -0.1700
Data Index: 3595539 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3513. Min Act: -0.1700
Data Index: 4600341 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3200. Min Act: -0.1700
Data Index: 3987345 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3200. Min Act: -0.1700
Data Index: 7081803 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3200. Min Act: -0.1700
Data Index: 1439028 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.2888. Min Act: -0.1700
Data Index: 7437378 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.2888. Min Act: -0.1700
Data Index: 6710379 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.3200. Min Act: -0.1700
Data Index: 6637079 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.2575. Min Act: -0.1700
Data Index: 4580131 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.2575. Min Act: -0.1700
Data Index: 3571101 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.2575. Min Act: -0.1700
Data Index: 2440524 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6013. Min Range: -4.6013
Max Act: 4.2575. Min Act: -0.1700
Data Index: 223413 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19