Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1539 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6605758 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.5921. Min Act: -0.1700
Data Index: 4792039 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.5296. Min Act: -0.1700
Data Index: 5967652 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.4984. Min Act: -0.1700
Data Index: 3597305 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.4984. Min Act: -0.1700
Data Index: 4818166 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.4984. Min Act: -0.1700
Data Index: 7269343 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 3072235 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.4359. Min Act: -0.1700
Data Index: 2687694 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.4046. Min Act: -0.1700
Data Index: 6707050 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 7173700 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.4046. Min Act: -0.1700
Data Index: 6707046 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 2507560 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 2916680 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 1241373 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3109. Min Act: -0.1700
Data Index: 89447 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3421. Min Act: -0.1700
Data Index: 2708896 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 259814 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.3421. Min Act: -0.1695
Data Index: 2046250 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.2796. Min Act: -0.1700
Data Index: 2711299 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5921. Min Range: -5.5921
Max Act: 5.2796. Min Act: -0.1700
Data Index: 3921907 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19