Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5509 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.4579. Min Act: -0.1700
Data Index: 5761856 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.2079. Min Act: -0.1700
Data Index: 5822114 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1141. Min Act: -0.1700
Data Index: 5186491 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.1141. Min Act: -0.1700
Data Index: 4464601 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0829. Min Act: -0.1700
Data Index: 1584660 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4579. Min Range: -5.4579
Max Act: 5.0829. Min Act: -0.1700
Data Index: 1428225 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.9891. Min Act: -0.1700
Data Index: 1428227 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.9891. Min Act: -0.1700
Data Index: 1998577 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1927842 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7458581 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8641. Min Act: -0.1700
Data Index: 5214423 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8641. Min Act: -0.1700
Data Index: 5214424 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8329. Min Act: -0.1700
Data Index: 6053689 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7306227 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8329. Min Act: -0.1700
Data Index: 8160041 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8329. Min Act: -0.1700
Data Index: 5328925 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8329. Min Act: -0.1700
Data Index: 4464603 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8329. Min Act: -0.1700
Data Index: 3103409 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.8016. Min Act: -0.1700
Data Index: 5214430 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4579. Min Range: -5.4579
Max Act: 4.7704. Min Act: -0.1700
Data Index: 4987349 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19