Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5718 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.9704. Min Act: -0.1700
Data Index: 8571800 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.7829. Min Act: -0.1700
Data Index: 3598747 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.7829. Min Act: -0.1700
Data Index: 7728927 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.7204. Min Act: -0.1700
Data Index: 4520761 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.5641. Min Act: -0.1700
Data Index: 2837810 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.5329. Min Act: -0.1700
Data Index: 7203856 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.5016. Min Act: -0.1700
Data Index: 4488348 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.5016. Min Act: -0.1700
Data Index: 7625505 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4704. Min Act: -0.1700
Data Index: 6082362 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4704. Min Act: -0.1700
Data Index: 7255923 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4391. Min Act: -0.1700
Data Index: 2751927 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4391. Min Act: -0.1700
Data Index: 3971002 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4391. Min Act: -0.1700
Data Index: 8366559 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4391. Min Act: -0.1700
Data Index: 5879942 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.4079. Min Act: -0.1700
Data Index: 862912 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.3766. Min Act: -0.1700
Data Index: 6408656 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.3766. Min Act: -0.1700
Data Index: 6339590 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.3454. Min Act: -0.1700
Data Index: 511959 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.3141. Min Act: -0.1700
Data Index: 8717984 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9704. Min Range: -7.9704
Max Act: 7.3141. Min Act: -0.1700
Data Index: 604390 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19