Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5083. Min Range: -7.5083
Max Act: 7.5083. Min Act: -0.1700
Data Index: 7988654 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5083. Min Range: -7.5083
Max Act: 7.1333. Min Act: -0.1700
Data Index: 679329 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5083. Min Range: -7.5083
Max Act: 7.0708. Min Act: -0.1700
Data Index: 6043047 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5083. Min Range: -7.5083
Max Act: 7.0708. Min Act: -0.1700
Data Index: 8601957 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.9146. Min Act: -0.1700
Data Index: 6824011 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.8833. Min Act: -0.1700
Data Index: 5448706 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.7896. Min Act: -0.1700
Data Index: 7314785 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.7271. Min Act: -0.1700
Data Index: 3692540 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.6646. Min Act: -0.1700
Data Index: 2718368 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.6333. Min Act: -0.1700
Data Index: 1791520 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.6021. Min Act: -0.1700
Data Index: 5003466 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.6021. Min Act: -0.1700
Data Index: 4613376 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5708. Min Act: -0.1700
Data Index: 4723400 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5708. Min Act: -0.1700
Data Index: 2017514 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5708. Min Act: -0.1700
Data Index: 6187722 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5396. Min Act: -0.1700
Data Index: 7517224 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5396. Min Act: -0.1700
Data Index: 4189455 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5083. Min Act: -0.1700
Data Index: 4921421 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5083. Min Act: -0.1700
Data Index: 2768463 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5083. Min Range: -7.5083
Max Act: 6.5083. Min Act: -0.1700
Data Index: 6759433 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19