Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.3013. Min Act: -0.1700
Data Index: 7486524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3013. Min Range: -5.3013
Max Act: 5.3013. Min Act: -0.1700
Data Index: 5626569 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9888. Min Act: -0.1700
Data Index: 1346850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 1607515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2109512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8211357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 7928576 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 7259130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 506268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8774306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 469382 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 2166083 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 5580669 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8402478 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.7701. Min Act: -0.1700
Data Index: 3624011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.7701. Min Act: -0.1700
Data Index: 5659911 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.7701. Min Act: -0.1700
Data Index: 6697036 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.7701. Min Act: -0.1700
Data Index: 582200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.7701. Min Act: -0.1700
Data Index: 977620 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3013. Min Range: -5.3013
Max Act: 4.7701. Min Act: -0.1700
Data Index: 3082679 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19