Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1457 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.3687. Min Act: -0.1700
Data Index: 6245507 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.3062. Min Act: -0.1700
Data Index: 3207412 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.2125. Min Act: -0.1700
Data Index: 5025752 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1812. Min Act: -0.1700
Data Index: 2897778 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1500. Min Act: -0.1700
Data Index: 6398291 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1812. Min Act: -0.1700
Data Index: 2107094 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1500. Min Act: -0.1700
Data Index: 7885285 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1500. Min Act: -0.1700
Data Index: 885921 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0875. Min Act: -0.1700
Data Index: 6804725 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0875. Min Act: -0.1700
Data Index: 5953586 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0562. Min Act: -0.1700
Data Index: 2396590 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0562. Min Act: -0.1700
Data Index: 2673644 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0250. Min Act: -0.1700
Data Index: 6879155 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9937. Min Act: -0.1700
Data Index: 363170 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9625. Min Act: -0.1700
Data Index: 7864388 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9625. Min Act: -0.1700
Data Index: 3371612 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9312. Min Act: -0.1700
Data Index: 835155 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9312. Min Act: -0.1700
Data Index: 4955259 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9000. Min Act: -0.1700
Data Index: 3040641 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.8687. Min Act: -0.1700
Data Index: 5644750 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19