Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.3589. Min Act: -0.1700
Data Index: 2026873 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.3589. Min Act: -0.1700
Data Index: 6376406 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.3589. Min Act: -0.1700
Data Index: 4469306 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 1274222 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 6765599 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 1989736 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 1618699 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 5585384 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 5289478 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 5079552 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 5008654 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 4724510 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 2026093 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 4388887 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 3985337 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 3461872 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 3354355 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 1015097 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 2505864 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3589. Min Range: -8.3589
Max Act: 8.2339. Min Act: -0.1700
Data Index: 966950 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19