Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1610 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6187. Min Range: -6.6187
Max Act: 6.6187. Min Act: -0.1700
Data Index: 1308513 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6187. Min Range: -6.6187
Max Act: 6.2124. Min Act: -0.1700
Data Index: 2453075 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6187. Min Range: -6.6187
Max Act: 6.0562. Min Act: -0.1700
Data Index: 4034377 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6187. Min Range: -6.6187
Max Act: 6.0249. Min Act: -0.1700
Data Index: 8721334 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6187. Min Range: -6.6187
Max Act: 6.0249. Min Act: -0.1700
Data Index: 2219841 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9624. Min Act: -0.1700
Data Index: 8624300 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9937. Min Act: -0.1700
Data Index: 4768379 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9624. Min Act: -0.1700
Data Index: 8411137 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9624. Min Act: -0.1700
Data Index: 3839219 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9624. Min Act: -0.1700
Data Index: 1279528 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9312. Min Act: -0.1700
Data Index: 501621 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9312. Min Act: -0.1700
Data Index: 7070180 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9624. Min Act: -0.1700
Data Index: 333355 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.8999. Min Act: -0.1700
Data Index: 8345073 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.9312. Min Act: -0.1700
Data Index: 6217761 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.8999. Min Act: -0.1700
Data Index: 1328721 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.8687. Min Act: -0.1700
Data Index: 922827 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.8374. Min Act: -0.1700
Data Index: 3648762 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.8687. Min Act: -0.1700
Data Index: 389491 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6187. Min Range: -6.6187
Max Act: 5.8687. Min Act: -0.1700
Data Index: 7496679 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19