Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6108 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.7192. Min Act: -0.1700
Data Index: 503521 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5748. Min Act: -0.1700
Data Index: 8168232 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5586. Min Act: -0.1700
Data Index: 3206409 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5586. Min Act: -0.1700
Data Index: 2791238 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5263. Min Act: -0.1700
Data Index: 7464300 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5425. Min Act: -0.1700
Data Index: 4992046 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5263. Min Act: -0.1700
Data Index: 5950818 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5102. Min Act: -0.1700
Data Index: 6738697 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5102. Min Act: -0.1700
Data Index: 1886241 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5102. Min Act: -0.1700
Data Index: 8181723 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5102. Min Act: -0.1700
Data Index: 3349826 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.5102. Min Act: -0.1700
Data Index: 805711 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 4858135 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 8096880 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 7861541 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 171122 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 7085786 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 4344665 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 4183356 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7192. Min Range: -2.7192
Max Act: 2.4940. Min Act: -0.1700
Data Index: 3638557 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19