Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.7766. Min Act: -0.1700
Data Index: 47891 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.7766. Min Act: -0.1700
Data Index: 3616271 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.7141. Min Act: -0.1700
Data Index: 1950498 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.6829. Min Act: -0.1700
Data Index: 52310 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.6829. Min Act: -0.1700
Data Index: 3318558 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.6516. Min Act: -0.1700
Data Index: 8066473 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.6516. Min Act: -0.1700
Data Index: 8435310 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.6516. Min Act: -0.1700
Data Index: 5867992 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.6204. Min Act: -0.1700
Data Index: 541102 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 8611298 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 8337499 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 1886292 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 5292693 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5891. Min Act: -0.1700
Data Index: 868709 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5579. Min Act: -0.1700
Data Index: 2131211 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5579. Min Act: -0.1700
Data Index: 1719023 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5579. Min Act: -0.1700
Data Index: 8561646 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5579. Min Act: -0.1700
Data Index: 8501730 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5579. Min Act: -0.1700
Data Index: 5516 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7766. Min Range: -6.7766
Max Act: 6.5266. Min Act: -0.1700
Data Index: 5596795 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19