Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.7939. Min Act: -0.1700
Data Index: 7329978 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.7314. Min Act: -0.1700
Data Index: 765753 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.7314. Min Act: -0.1700
Data Index: 7228249 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.7001. Min Act: -0.1700
Data Index: 4036363 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.7314. Min Act: -0.1700
Data Index: 3570247 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.7001. Min Act: -0.1700
Data Index: 2687455 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6689. Min Act: -0.1700
Data Index: 88340 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6689. Min Act: -0.1700
Data Index: 1426767 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6376. Min Act: -0.1700
Data Index: 528417 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6064. Min Act: -0.1700
Data Index: 568717 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.5751. Min Act: -0.1700
Data Index: 2059366 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6064. Min Act: -0.1700
Data Index: 1415351 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6064. Min Act: -0.1700
Data Index: 1878296 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6064. Min Act: -0.1700
Data Index: 6011688 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6064. Min Act: -0.1700
Data Index: 4451576 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.6064. Min Act: -0.1700
Data Index: 6058364 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.5751. Min Act: -0.1700
Data Index: 6313068 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.5751. Min Act: -0.1700
Data Index: 5781928 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.5751. Min Act: -0.1700
Data Index: 1035366 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7939. Min Range: -5.7939
Max Act: 5.5439. Min Act: -0.1700
Data Index: 4355785 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19