Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0123. Min Range: -2.0123
Max Act: 2.0123. Min Act: -0.1700
Data Index: 6268898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 2137469 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 6268893 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 2420602 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 5978867 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 5914478 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 5256744 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 2547729 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 4747448 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 2211952 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 1027327 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 4725564 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 1586789 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 6223761 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 675968 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 4294446 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 4013151 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 3653477 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 1886621 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0123. Min Range: -2.0123
Max Act: 1.9954. Min Act: -0.1700
Data Index: 3280046 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19