Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5785 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0999. Min Range: -6.0999
Max Act: 6.0999. Min Act: -0.1700
Data Index: 2569587 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0999. Min Range: -6.0999
Max Act: 6.0999. Min Act: -0.1700
Data Index: 41756 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0999. Min Range: -6.0999
Max Act: 6.0061. Min Act: -0.1700
Data Index: 2936661 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0999. Min Range: -6.0999
Max Act: 6.0061. Min Act: -0.1700
Data Index: 8449357 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.9124. Min Act: -0.1700
Data Index: 2586789 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.8811. Min Act: -0.1700
Data Index: 8716574 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.8186. Min Act: -0.1700
Data Index: 4170639 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7561. Min Act: -0.1700
Data Index: 2420705 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7874. Min Act: -0.1700
Data Index: 7708784 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7561. Min Act: -0.1700
Data Index: 286166 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7561. Min Act: -0.1700
Data Index: 339280 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7561. Min Act: -0.1700
Data Index: 2317877 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7249. Min Act: -0.1700
Data Index: 5755094 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.7249. Min Act: -0.1700
Data Index: 6006634 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.6936. Min Act: -0.1700
Data Index: 2155155 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.6936. Min Act: -0.1700
Data Index: 5799698 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.6936. Min Act: -0.1700
Data Index: 3565826 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.6624. Min Act: -0.1700
Data Index: 5779184 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.6624. Min Act: -0.1700
Data Index: 2728983 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0999. Min Range: -6.0999
Max Act: 5.6624. Min Act: -0.1700
Data Index: 8026987 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19