Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 567 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.7821. Min Act: -0.1700
Data Index: 3102305 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.7502. Min Act: -0.1700
Data Index: 92492 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.7182. Min Act: -0.1700
Data Index: 3845940 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.7022. Min Act: -0.1700
Data Index: 949793 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6862. Min Act: -0.1700
Data Index: 1444877 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 2065914 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 6493019 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 743288 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 3060906 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 5897528 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 5136469 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 4774613 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 3575613 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 4742687 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 4716106 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 3929143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 1300306 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 3689337 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 4662835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7821. Min Range: -2.7821
Max Act: 2.6702. Min Act: -0.1700
Data Index: 4411178 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19