Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.8025. Min Act: -0.1700
Data Index: 5889035 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.5837. Min Act: -0.1700
Data Index: 5091459 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.5525. Min Act: -0.1700
Data Index: 2079434 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.5212. Min Act: -0.1700
Data Index: 620564 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.5212. Min Act: -0.1700
Data Index: 3703283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.4900. Min Act: -0.1700
Data Index: 4806536 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.3962. Min Act: -0.1700
Data Index: 873090 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.4275. Min Act: -0.1700
Data Index: 5836903 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.3962. Min Act: -0.1700
Data Index: 7091802 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.3025. Min Act: -0.1700
Data Index: 1024924 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2712. Min Act: -0.1700
Data Index: 1996880 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2712. Min Act: -0.1700
Data Index: 7855508 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2712. Min Act: -0.1699
Data Index: 8106833 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2087. Min Act: -0.1700
Data Index: 7559142 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2400. Min Act: -0.1700
Data Index: 6490242 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2400. Min Act: -0.1700
Data Index: 564825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2087. Min Act: -0.1700
Data Index: 2236897 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.2087. Min Act: -0.1700
Data Index: 3378256 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.1775. Min Act: -0.1700
Data Index: 4106433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8025. Min Range: -4.8025
Max Act: 4.1775. Min Act: -0.1700
Data Index: 5464390 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19