Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.7007. Min Act: -0.1700
Data Index: 8003988 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.5757. Min Act: -0.1700
Data Index: 3963108 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.6070. Min Act: -0.1700
Data Index: 561652 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.5757. Min Act: -0.1700
Data Index: 6886837 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.5445. Min Act: -0.1700
Data Index: 2300062 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.5132. Min Act: -0.1700
Data Index: 6995780 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.5445. Min Act: -0.1700
Data Index: 6431340 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4820. Min Act: -0.1700
Data Index: 4462502 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4820. Min Act: -0.1700
Data Index: 6564081 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4507. Min Act: -0.1700
Data Index: 945167 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4507. Min Act: -0.1700
Data Index: 3492604 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4195. Min Act: -0.1700
Data Index: 7178425 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4507. Min Act: -0.1700
Data Index: 3210846 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4195. Min Act: -0.1700
Data Index: 6043876 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.3882. Min Act: -0.1700
Data Index: 7126613 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4195. Min Act: -0.1700
Data Index: 1558995 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.3882. Min Act: -0.1700
Data Index: 1336079 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4195. Min Act: -0.1700
Data Index: 3064367 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4195. Min Act: -0.1700
Data Index: 923856 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7007. Min Range: -4.7007
Max Act: 4.4195. Min Act: -0.1700
Data Index: 848663 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19