Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0089. Min Range: -3.0089
Max Act: 3.0089. Min Act: -0.1700
Data Index: 4965229 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9931. Min Act: -0.1700
Data Index: 2129634 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9773. Min Act: -0.1700
Data Index: 331807 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9773. Min Act: -0.1700
Data Index: 3569656 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9614. Min Act: -0.1700
Data Index: 5805070 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9298. Min Act: -0.1700
Data Index: 7860891 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9298. Min Act: -0.1700
Data Index: 6807730 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9298. Min Act: -0.1700
Data Index: 2754996 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9298. Min Act: -0.1700
Data Index: 6234927 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9456. Min Act: -0.1700
Data Index: 11579 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9139. Min Act: -0.1700
Data Index: 6370221 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9298. Min Act: -0.1700
Data Index: 5088861 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9139. Min Act: -0.1700
Data Index: 2786955 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9139. Min Act: -0.1700
Data Index: 8696906 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.8981. Min Act: -0.1700
Data Index: 1749537 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.8981. Min Act: -0.1700
Data Index: 8608628 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.8981. Min Act: -0.1700
Data Index: 3516760 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9139. Min Act: -0.1700
Data Index: 7845910 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.9139. Min Act: -0.1700
Data Index: 7511817 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0089. Min Range: -3.0089
Max Act: 2.8822. Min Act: -0.1700
Data Index: 6557594 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19