Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.8142. Min Act: -0.1700
Data Index: 324055 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.7204. Min Act: -0.1700
Data Index: 6540539 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.7204. Min Act: -0.1700
Data Index: 7125723 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.6892. Min Act: -0.1700
Data Index: 5488088 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.5954. Min Act: -0.1700
Data Index: 8577296 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.6267. Min Act: -0.1700
Data Index: 6455652 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.5329. Min Act: -0.1700
Data Index: 5120596 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.5329. Min Act: -0.1700
Data Index: 1904222 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.5017. Min Act: -0.1700
Data Index: 8214766 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.5017. Min Act: -0.1700
Data Index: 2478731 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.5017. Min Act: -0.1700
Data Index: 6780924 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.4392. Min Act: -0.1700
Data Index: 6663418 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.4079. Min Act: -0.1700
Data Index: 7229615 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3767. Min Act: -0.1700
Data Index: 4920904 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3454. Min Act: -0.1700
Data Index: 2859199 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3454. Min Act: -0.1700
Data Index: 2137961 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3454. Min Act: -0.1700
Data Index: 611841 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3454. Min Act: -0.1700
Data Index: 8075643 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3454. Min Act: -0.1700
Data Index: 7729763 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8142. Min Range: -6.8142
Max Act: 6.3142. Min Act: -0.1700
Data Index: 4431289 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19