Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.9000. Min Act: -0.1700
Data Index: 4768069 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.8062. Min Act: -0.1700
Data Index: 1621768 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7750. Min Act: -0.1700
Data Index: 265071 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7750. Min Act: -0.1700
Data Index: 2792057 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7750. Min Act: -0.1700
Data Index: 4432059 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7125. Min Act: -0.1700
Data Index: 342118 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7125. Min Act: -0.1700
Data Index: 8053872 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7125. Min Act: -0.1700
Data Index: 1550294 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7125. Min Act: -0.1700
Data Index: 1828309 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.7125. Min Act: -0.1700
Data Index: 2684693 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6812. Min Act: -0.1700
Data Index: 342107 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6187. Min Act: -0.1700
Data Index: 5350682 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6187. Min Act: -0.1700
Data Index: 8120486 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6500. Min Act: -0.1700
Data Index: 945431 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6187. Min Act: -0.1700
Data Index: 3149811 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6187. Min Act: -0.1700
Data Index: 2773524 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6187. Min Act: -0.1700
Data Index: 1920545 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.6187. Min Act: -0.1700
Data Index: 8029971 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.5875. Min Act: -0.1700
Data Index: 4727945 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9000. Min Range: -5.9000
Max Act: 5.5562. Min Act: -0.1700
Data Index: 4654546 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19