Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.8912. Min Act: -0.1700
Data Index: 302234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.8600. Min Act: -0.1700
Data Index: 5930077 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7975. Min Act: -0.1700
Data Index: 8551498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7975. Min Act: -0.1700
Data Index: 1004362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7975. Min Act: -0.1700
Data Index: 4935609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7662. Min Act: -0.1700
Data Index: 4632927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7662. Min Act: -0.1700
Data Index: 6411605 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7662. Min Act: -0.1700
Data Index: 7044696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7350. Min Act: -0.1700
Data Index: 2858929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7350. Min Act: -0.1700
Data Index: 3573131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7350. Min Act: -0.1700
Data Index: 3584552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7350. Min Act: -0.1700
Data Index: 597227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7350. Min Act: -0.1700
Data Index: 4965601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 5190533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 3944485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 6093000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 6485963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 2910107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 4797973 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8912. Min Range: -4.8912
Max Act: 4.7037. Min Act: -0.1700
Data Index: 6087673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19