Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.5050. Min Act: -0.1700
Data Index: 2585561 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.5050. Min Act: -0.1700
Data Index: 4860306 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.4737. Min Act: -0.1700
Data Index: 5909305 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.4737. Min Act: -0.1700
Data Index: 5977067 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.4425. Min Act: -0.1700
Data Index: 4289625 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.4112. Min Act: -0.1700
Data Index: 1656055 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.3800. Min Act: -0.1700
Data Index: 98319 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.3800. Min Act: -0.1700
Data Index: 2915031 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.3800. Min Act: -0.1700
Data Index: 8309922 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.3487. Min Act: -0.1700
Data Index: 5566634 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.3487. Min Act: -0.1700
Data Index: 3971167 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.3487. Min Act: -0.1700
Data Index: 1271617 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2862. Min Act: -0.1700
Data Index: 3216883 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2550. Min Act: -0.1700
Data Index: 3620704 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2550. Min Act: -0.1700
Data Index: 1403923 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2237. Min Act: -0.1700
Data Index: 8521736 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2237. Min Act: -0.1700
Data Index: 3986330 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2237. Min Act: -0.1700
Data Index: 2939156 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2237. Min Act: -0.1700
Data Index: 6204002 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5050. Min Range: -5.5050
Max Act: 5.2237. Min Act: -0.1700
Data Index: 4697186 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19