Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6719. Min Act: -0.1700
Data Index: 6897296 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4216042 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 7349327 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 2062641 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 3093807 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 6907606 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 637999 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 2973533 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4706068 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4119118 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6094. Min Act: -0.1700
Data Index: 1821863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5781. Min Act: -0.1700
Data Index: 586707 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5781. Min Act: -0.1700
Data Index: 582066 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6094. Min Act: -0.1700
Data Index: 6864992 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6406. Min Act: -0.1700
Data Index: 5313563 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.6094. Min Act: -0.1700
Data Index: 8423014 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5781. Min Act: -0.1700
Data Index: 3916826 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5781. Min Act: -0.1700
Data Index: 3952103 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5469. Min Act: -0.1700
Data Index: 2448938 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6719. Min Range: -4.6719
Max Act: 4.5469. Min Act: -0.1700
Data Index: 935601 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19