Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1205 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.6755. Min Act: -0.1700
Data Index: 8436150 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.6130. Min Act: -0.1700
Data Index: 3366528 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.6130. Min Act: -0.1700
Data Index: 3230977 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5817. Min Act: -0.1700
Data Index: 7901317 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5817. Min Act: -0.1700
Data Index: 8346983 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5505. Min Act: -0.1700
Data Index: 5294922 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5505. Min Act: -0.1700
Data Index: 3706456 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5505. Min Act: -0.1700
Data Index: 7210194 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5817. Min Act: -0.1700
Data Index: 5165209 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5192. Min Act: -0.1700
Data Index: 4215766 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5505. Min Act: -0.1700
Data Index: 3316877 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4880. Min Act: -0.1700
Data Index: 5122001 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.5192. Min Act: -0.1700
Data Index: 1760776 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4880. Min Act: -0.1699
Data Index: 3949699 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4880. Min Act: -0.1700
Data Index: 372926 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4880. Min Act: -0.1700
Data Index: 5018580 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4880. Min Act: -0.1700
Data Index: 4106564 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4255. Min Act: -0.1700
Data Index: 899126 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4567. Min Act: -0.1700
Data Index: 4186554 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6755. Min Range: -6.6755
Max Act: 6.4567. Min Act: -0.1700
Data Index: 6577408 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19