Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.9125. Min Act: -0.1700
Data Index: 5124837 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.7875. Min Act: -0.1700
Data Index: 7141368 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.7562. Min Act: -0.1700
Data Index: 1878893 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6625. Min Act: -0.1700
Data Index: 6539899 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6937. Min Act: -0.1700
Data Index: 2643662 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6937. Min Act: -0.1700
Data Index: 5286318 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5919329 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5712519 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6312. Min Act: -0.1700
Data Index: 4211915 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5687. Min Act: -0.1700
Data Index: 6539900 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6000. Min Act: -0.1700
Data Index: 1635107 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5687. Min Act: -0.1700
Data Index: 7512796 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.6000. Min Act: -0.1700
Data Index: 8464548 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5980256 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5375. Min Act: -0.1700
Data Index: 1869514 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5375. Min Act: -0.1700
Data Index: 1061843 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.4750. Min Act: -0.1700
Data Index: 7086819 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6902825 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5062. Min Act: -0.1700
Data Index: 5884784 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9125. Min Range: -4.9125
Max Act: 4.5062. Min Act: -0.1700
Data Index: 1405619 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19